Gemma 4 26B A4B Behavioral Fingerprint

How Google's Gemma 4 26B A4B 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

7 / 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

30 / 30 answers

Favorite color

azure

22 / 30 answers

Coin flip: heads

100%

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 = 0.00 bit · uniform baseline 1.00 bit

AnswerCountShare
heads30100.0%

Favorite number · English

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

AnswerCountShare
4230100.0%

Favorite number · Chinese

n = 30 · H = 1.20 bit · uniform baseline 13.29 bit

AnswerCountShare
71963.3%
42930.0%
426.7%

Random animal · English

n = 30 · H = 0.65 bit · uniform baseline 5.64 bit

AnswerCountShare
capybara2583.3%
elephant516.7%

Random animal · Chinese

n = 30 · H = 1.03 bit · uniform baseline 5.64 bit

AnswerCountShare
老虎2170.0%
熊猫826.7%
袋鼠13.3%

Random city · English

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

AnswerCountShare
tokyo30100.0%

Random city · Chinese

n = 30 · H = 1.88 bit · uniform baseline 5.64 bit

AnswerCountShare
东京1033.3%
伦敦1033.3%
上海723.3%
巴黎310.0%

Random color · English

n = 30 · H = 1.25 bit · uniform baseline 4.91 bit

AnswerCountShare
azure2273.3%
blue516.7%
crimson13.3%
cyan13.3%
magenta13.3%

Random color · Chinese

n = 30 · H = 0.35 bit · uniform baseline 4.91 bit

AnswerCountShare
2893.3%
26.7%

Random letter · English

n = 30 · H = 0.00 bit · uniform baseline 4.70 bit

AnswerCountShare
q30100.0%

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 = 0.00 bit · uniform baseline 6.64 bit

AnswerCountShare
4230100.0%

Random number 1-100 · Chinese

n = 30 · H = 0.00 bit · uniform baseline 6.64 bit

AnswerCountShare
4230100.0%

Want to verify your API really serves Gemma 4 26B A4B ?

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 4 26B A4B Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai