INDEX

Explanations

import from asset

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

the word "is" or similar short linking verbs/copulas in declarative statements.

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

The neuron activates on occurrences of the Python keyword “import.”

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

 erstes

-1.41

 ráp

-1.37

 rác

-1.34

یکه

-1.27

 ganze

-1.25

：……

-1.24

 Reduce

-1.21

</h4>

-1.21

 einzel

-1.20

 altes

-1.20

POSITIVE LOGITS

if

1.85

 ketika

1.48

 because

1.45

ssss

1.42

ss

1.40

స్

1.39

čenie

1.37

༤

1.37

 then

1.36

sssss

1.35

Activations Density 1.171%

import from asset

the word "is" or similar short linking verbs/copulas in declarative statements.

The neuron activates on occurrences of the Python keyword “import.”

No Comments

No Known Activations

import from asset

the word "is" or similar short linking verbs/copulas in declarative statements.

The neuron activates on occurrences of the Python keyword “import.”

No Comments

No Known Activations