Gemma 3 12B Behavioral Fingerprint

How Google's Gemma 3 12B answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 450 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

450

Randomness score

10 / 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

28 / 30 answers

Favorite color

blue

26 / 30 answers

Coin flip: heads

98%

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 = 0.00 bit · uniform baseline 1.00 bit

AnswerCountShare
heads30100.0%

Coin flip · Chinese

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

AnswerCountShare
heads2996.7%
tails13.3%

Favorite number · English

n = 30 · H = 0.00 bit · uniform baseline 13.29 bit

AnswerCountShare
730100.0%

Favorite number · Chinese

n = 30 · H = 0.21 bit · uniform baseline 13.29 bit

AnswerCountShare
72996.7%
313.3%

Random animal · English

n = 30 · H = 0.84 bit · uniform baseline 5.64 bit

AnswerCountShare
dog2273.3%
elephant826.7%

Random animal · Chinese

n = 30 · H = 1.16 bit · uniform baseline 5.64 bit

AnswerCountShare
1756.7%
1240.0%
老虎13.3%

Random city · English

n = 30 · H = 1.35 bit · uniform baseline 5.64 bit

AnswerCountShare
london1550.0%
denver1343.3%
chicago13.3%
tokyo13.3%

Random city · Chinese

n = 30 · H = 0.67 bit · uniform baseline 5.64 bit

AnswerCountShare
东京2686.7%
巴黎310.0%
伦敦13.3%

Random color · English

n = 30 · H = 0.70 bit · uniform baseline 4.91 bit

AnswerCountShare
blue2686.7%
purple26.7%
green26.7%

Random color · Chinese

n = 30 · H = 0.21 bit · uniform baseline 4.91 bit

AnswerCountShare
2996.7%
绿13.3%

Random letter · English

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

AnswerCountShare
q2583.3%
z413.3%
k13.3%

Random number 1-10 · English

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

AnswerCountShare
730100.0%

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 = 0.42 bit · uniform baseline 6.64 bit

AnswerCountShare
422893.3%
5713.3%
7313.3%

Random number 1-100 · Chinese

n = 30 · H = 0.70 bit · uniform baseline 6.64 bit

AnswerCountShare
422686.7%
3726.7%
7326.7%

Want to verify your API really serves Gemma 3 12B?

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 12B Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai