INDEX

Explanations

foreign or specific contexts

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

The neuron fires on standalone numeric tokens (years, counts, and other digit sequences).

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

line breaks or whitespace characters, particularly tab characters used for indentation.

oai_token-act-pair · claude-4-5-sonnet Triggered by @jyhe0408

mentions of ordinal rankings or placements in results lists.

oai_token-act-pair · gpt-5 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

-1.56

$(

-1.24

 from

-1.16

اتل

-1.16

 which

-1.09

оо

-1.09

 skues

-1.09

！（

-1.07

 Give

-1.06

 even

-1.05

POSITIVE LOGITS

 deline

1.24

 solchen

1.16

 alcune

1.14

 moron

1.13

 derselben

1.12

 arou

1.11

 déterminer

1.11

 solch

1.09

裆

1.07

 Toutefois

1.04

Activations Density 0.000%

foreign or specific contexts

The neuron fires on standalone numeric tokens (years, counts, and other digit sequences).

line breaks or whitespace characters, particularly tab characters used for indentation.

mentions of ordinal rankings or placements in results lists.

No Comments

No Known Activations

foreign or specific contexts

The neuron fires on standalone numeric tokens (years, counts, and other digit sequences).

line breaks or whitespace characters, particularly tab characters used for indentation.

mentions of ordinal rankings or placements in results lists.

No Comments

No Known Activations