INDEX

Explanations

stigma and related words

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

words and concepts related to stigma, especially in medical and social contexts.

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

This neuron detects occurrences of the root “stigma” (e.g., stigma, stigmatization, stigmatising).

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

溦

-2.53

 resounding

-2.31

梛

-2.23

！"

-2.22

</i>

-2.14

都不知道

-2.13

熥

-2.11

餿

-2.11

").

-2.09

 meager

-2.08

POSITIVE LOGITS

’

2.41

welche

2.14

 podem

2.00

᩠

1.89

侂

1.88

 começaram

1.88

</h4>

1.87

 เพื่อ

1.86

1.85

 необходимость

1.85

Activations Density 0.004%

stigma and related words

words and concepts related to stigma, especially in medical and social contexts.

This neuron detects occurrences of the root “stigma” (e.g., stigma, stigmatization, stigmatising).

No Comments

No Known Activations

stigma and related words

words and concepts related to stigma, especially in medical and social contexts.

This neuron detects occurrences of the root “stigma” (e.g., stigma, stigmatization, stigmatising).

No Comments

No Known Activations