INDEX

Explanations

academic or scientific results

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

The neuron activates for opening parts of technical or academic texts, particularly when it encounters phrases like "of", "for", or "over" following content markers.

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

This neuron responds to numeric tokens—especially decimal numbers (e.g. “12.125,” “44.5,” “35.5,” etc.).

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

sich

-1.48

of

-1.46

 beleid

-1.40

ების

-1.38

荇

-1.34

kamen

-1.32

 Sistemas

-1.30

↵

-1.30

ſtra

-1.30

 primeiro

-1.29

POSITIVE LOGITS

can

1.63

いたしました

1.53

 same

1.47

Sedangkan

1.44

 entire

1.40

してきました

1.33

懦

1.31

Selanjutnya

1.29

 dificultad

1.28

土曜日

1.28

Activations Density 0.117%

academic or scientific results

The neuron activates for opening parts of technical or academic texts, particularly when it encounters phrases like "of", "for", or "over" following content markers.

This neuron responds to numeric tokens—especially decimal numbers (e.g. “12.125,” “44.5,” “35.5,” etc.).

No Comments

No Known Activations

academic or scientific results

The neuron activates for opening parts of technical or academic texts, particularly when it encounters phrases like "of", "for", or "over" following content markers.

This neuron responds to numeric tokens—especially decimal numbers (e.g. “12.125,” “44.5,” “35.5,” etc.).

No Comments

No Known Activations