INDEX

Explanations

missense mutations

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

the word "sense" when preceded by certain letters (like "miss", "is", "ad"), typically appearing in technical or scientific contexts.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

The neuron consistently fires on the substring “ense,” i.e. words ending or containing “ense” (as in “missense,” “license,” etc.).

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

Not in Any Lists

No Comments

Negative Logits

 dunklen

-2.58

 Primarily

-2.48

 говорили

-2.44

 Contrary

-2.39

-2.38

 Notably

-2.36

 Extremely

-2.31

 predetermined

-2.30

 Possibly

-2.30

 greatest

-2.30

POSITIVE LOGITS

ense

3.48

ܞ

2.72

2.33

亖

2.27

ens

2.20

 they

2.17

ть

2.16

佧

2.14

Ꮉ

2.08

ENSE

2.06

Activations Density 0.012%

missense mutations

the word "sense" when preceded by certain letters (like "miss", "is", "ad"), typically appearing in technical or scientific contexts.

The neuron consistently fires on the substring “ense,” i.e. words ending or containing “ense” (as in “missense,” “license,” etc.).

No Comments

No Known Activations

missense mutations

the word "sense" when preceded by certain letters (like "miss", "is", "ad"), typically appearing in technical or scientific contexts.

The neuron consistently fires on the substring “ense,” i.e. words ending or containing “ense” (as in “missense,” “license,” etc.).

No Comments

No Known Activations