INDEX

Explanations

health and safety matters

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

technical and scientific terms in specialized contexts.

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

The neuron strongly activates on key domain-specific nouns (especially hazards, medical conditions, treatments, technical systems, etc.) in factual/expository text.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/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

 which

-1.61

 what

-1.52

 статті

-1.50

but

-1.45

we

-1.28

ctique

-1.25

 سيكون

-1.24

客様

-1.23

you

-1.20

 söyl

-1.20

POSITIVE LOGITS

 vile

1.30

よい

1.28

 protective

1.28

 adept

1.27

BIÉN

1.25

地说

1.23

 السياس

1.20

谞

1.16

 przeznac

1.16

有三

1.16

Activations Density 0.202%

health and safety matters

technical and scientific terms in specialized contexts.

The neuron strongly activates on key domain-specific nouns (especially hazards, medical conditions, treatments, technical systems, etc.) in factual/expository text.

No Comments

No Known Activations

health and safety matters

technical and scientific terms in specialized contexts.

The neuron strongly activates on key domain-specific nouns (especially hazards, medical conditions, treatments, technical systems, etc.) in factual/expository text.

No Comments

No Known Activations