INDEX

Explanations

annotating and annotations

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

the word "annotate" and its variants (annotated, annotating, annotation).

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

The neuron fires on any form of the “annot” root (e.g. annotate, annotated, annotation) in a document.

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



-2.14

are

-2.13

ŚĆ

-2.03

秾

-2.02

ጪ

-2.02

就是

-2.00

 unmöglich

-1.99

she

-1.95

 ausreichend

-1.91

lossians

-1.91

POSITIVE LOGITS

↵

2.98

枓

2.45

</sup>

2.30

攆

2.30

“

2.30

 để

2.05

),”

2.00

 untuk

1.94

をご覧ください

1.94

ୈ

1.89

Activations Density 0.008%

annotating and annotations

the word "annotate" and its variants (annotated, annotating, annotation).

The neuron fires on any form of the “annot” root (e.g. annotate, annotated, annotation) in a document.

No Comments

No Known Activations

annotating and annotations

the word "annotate" and its variants (annotated, annotating, annotation).

The neuron fires on any form of the “annot” root (e.g. annotate, annotated, annotation) in a document.

No Comments

No Known Activations