Gemma 3 27B Behavioral Fingerprint

How Google's Gemma 3 27B answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 440 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).

Vendor

Google

Data generated

2026-07-08

Probe cells

15

Valid samples

440

Randomness score

9 / 100

Mean normalized entropy across cells, 0–100. 100 would be a uniform-random baseline; real models score far lower.

Signature answers

Favorite random number (1–100)

42

29 / 30 answers

Favorite color

blue

30 / 30 answers

Coin flip: heads

48%

Share of heads across coin-flip cells.

Answer distributions by probe cell

Empirical distributions of normalized one-word answers, per task and language. H is the Shannon entropy in bits; the uniform baseline is log2 of the answer-domain size.

Coin flip · English

n = 30 · H = 0.21 bit · uniform baseline 1.00 bit

AnswerCountShare
tails2996.7%
heads13.3%

Coin flip · Chinese

n = 26 · H = 0.00 bit · uniform baseline 1.00 bit

AnswerCountShare
heads26100.0%

Favorite number · English

n = 30 · H = 0.88 bit · uniform baseline 13.29 bit

AnswerCountShare
422170.0%
7930.0%

Favorite number · Chinese

n = 29 · H = 0.00 bit · uniform baseline 13.29 bit

AnswerCountShare
729100.0%

Random animal · English

n = 30 · H = 1.54 bit · uniform baseline 5.64 bit

AnswerCountShare
otter1860.0%
dog826.7%
elephant26.7%
tigersthought13.3%
penguin13.3%

Random animal · Chinese

n = 29 · H = 0.22 bit · uniform baseline 5.64 bit

AnswerCountShare
2896.6%
thought13.4%

Random city · English

n = 30 · H = 0.00 bit · uniform baseline 5.64 bit

AnswerCountShare
london30100.0%

Random city · Chinese

n = 29 · H = 1.73 bit · uniform baseline 5.64 bit

AnswerCountShare
伦敦1241.4%
东京1241.4%
巴黎310.3%
thought13.4%
纽约13.4%

Random color · English

n = 30 · H = 0.00 bit · uniform baseline 4.91 bit

AnswerCountShare
blue30100.0%

Random color · Chinese

n = 29 · H = 0.22 bit · uniform baseline 4.91 bit

AnswerCountShare
2896.6%
sootheaithought13.4%

Random letter · English

n = 30 · H = 0.77 bit · uniform baseline 4.70 bit

AnswerCountShare
g2686.7%
q26.7%
m13.3%
r13.3%

Random number 1-10 · English

n = 29 · H = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
729100.0%

Random number 1-10 · Chinese

n = 30 · H = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
730100.0%

Random number 1-100 · English

n = 30 · H = 0.21 bit · uniform baseline 6.64 bit

AnswerCountShare
422996.7%
3713.3%

Random number 1-100 · Chinese

n = 29 · H = 1.15 bit · uniform baseline 6.64 bit

AnswerCountShare
422275.9%
63310.3%
73310.3%
413.4%

Want to verify your API really serves Gemma 3 27B?

Point the free fingerprint checker at your endpoint: it samples the same probe questions from your browser and compares the distributions against this reference. Your API key never leaves your browser.

Verify your endpoint

Data source & license

Distributions: Tomáš Bruckner, "One Token Is Enough" (arXiv:2607.10252), official dataset Zenodo DOI 10.5281/zenodo.21278557, licensed CC-BY-4.0. Collected via OpenRouter at temperature 1.0 under the paper's fixed minimal one-word system prompt; answer keys are re-normalized with the checker's pipeline (color aliases, number words, coin h/t) so live probes are directly comparable.

Paper on arXivDataset on ZenodoCC-BY-4.0 license

More Google model fingerprints

Browse all 167 model fingerprints

Gemma 3 27B Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai