INDEX

Explanations

genetic and related topics

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

references to genetics or genetic concepts, especially the word "genetic" itself.

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

This neuron responds to uppercase or capitalized tokens—e.g. code keywords, constants, or proper-noun–style words.

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

</strong>

-3.22

神

-2.78

-2.72

-2.70

-2.55

<em>

-2.44

-2.36

for

-2.27

-2.25

has

-2.23

POSITIVE LOGITS

’

3.34

呶

2.48

racite

2.33

↵↵

2.28

绺

2.20

Of

2.19

 treinta

2.16

ৄ

2.16

sandalia

2.16

 vorigen

2.13

Activations Density 0.010%

genetic and related topics

references to genetics or genetic concepts, especially the word "genetic" itself.

This neuron responds to uppercase or capitalized tokens—e.g. code keywords, constants, or proper-noun–style words.

No Comments

No Known Activations

genetic and related topics

references to genetics or genetic concepts, especially the word "genetic" itself.

This neuron responds to uppercase or capitalized tokens—e.g. code keywords, constants, or proper-noun–style words.

No Comments

No Known Activations