INDEX

Explanations

amino acid

np_acts-logits-general · gemini-2.5-flash-lite

The neuron detects the phrase "amino acid" particularly in scientific contexts about protein composition.

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

This neuron does not consistently activate on any of the displayed tokens and thus does not appear to be detecting a reliably recurring pattern.

oai_token-act-pair · o4-mini

Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_10/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

喾

-2.80

籴

-2.61

了

-2.55



-2.53

缐

-2.42

丏

-2.41



-2.41

ſelves

-2.39

乀

-2.38

嵓

-2.34

POSITIVE LOGITS

2.66

 erfolgreichen

2.28

2.25

↵↵

2.14

ㄹ

2.11

the

2.11

蛧

2.11

2.09

一番

2.06

“

2.06

Activations Density 0.019%

amino acid

The neuron detects the phrase "amino acid" particularly in scientific contexts about protein composition.

This neuron does not consistently activate on any of the displayed tokens and thus does not appear to be detecting a reliably recurring pattern.

No Known Activations

amino acid

The neuron detects the phrase "amino acid" particularly in scientific contexts about protein composition.

This neuron does not consistently activate on any of the displayed tokens and thus does not appear to be detecting a reliably recurring pattern.

No Known Activations