INDEX

Explanations

social history, welfare, class, insects

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

The neuron detects the word "social" especially when used in academic or research contexts related to sociology, social welfare, or social relations.

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

The neuron specializes in detecting the word “social” (and its close derivatives, e.g. in “sociologist”).

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

we

-3.14



-3.13

隳

-3.09

 sorprender

-2.97

氿

-2.94

狴

-2.86

滹

-2.69

 Externe

-2.67

糨

-2.64

乀

-2.59

POSITIVE LOGITS

3.44

3.34

3.28

鋮

3.17

3.16

an

3.14

地说道

3.13

3.11

 debilitating

3.03

Activations Density 0.017%

social history, welfare, class, insects

The neuron detects the word "social" especially when used in academic or research contexts related to sociology, social welfare, or social relations.

The neuron specializes in detecting the word “social” (and its close derivatives, e.g. in “sociologist”).

No Comments

No Known Activations

social history, welfare, class, insects

The neuron detects the word "social" especially when used in academic or research contexts related to sociology, social welfare, or social relations.

The neuron specializes in detecting the word “social” (and its close derivatives, e.g. in “sociologist”).

No Comments

No Known Activations