INDEX

Explanations

natural habitat

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

descriptions of places, locations, or facilities, particularly focusing on characteristics and features of buildings, habitats, or venues.

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

The neuron strongly activates on copular-definition or usage statements—i.e. sentences of the form “X is a…,” “X is used for…,” “it is known as…,” etc.

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

-1.30

</h1>

-1.27

 miliki

-1.20

 Photographie

-1.20

all

-1.19

 that

-1.16

 their

-1.15

</h2>

-1.13

 your

-1.13

my

-1.13

POSITIVE LOGITS

これも

1.28

 contextLoads

1.26

搅拌

1.22

があり

1.20

PLING

1.19

 stylo

1.18

and

1.16

がありますが

1.16

这般

1.15

因为他

1.13

Activations Density 0.221%

natural habitat

descriptions of places, locations, or facilities, particularly focusing on characteristics and features of buildings, habitats, or venues.

The neuron strongly activates on copular-definition or usage statements—i.e. sentences of the form “X is a…,” “X is used for…,” “it is known as…,” etc.

No Comments

No Known Activations

natural habitat

descriptions of places, locations, or facilities, particularly focusing on characteristics and features of buildings, habitats, or venues.

The neuron strongly activates on copular-definition or usage statements—i.e. sentences of the form “X is a…,” “X is used for…,” “it is known as…,” etc.

No Comments

No Known Activations