INDEX

Explanations

biomarker proteins

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

technical or specialized terms within academic, mathematical, or technical contexts.

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

The neuron responds to relatively rare or content-rich words (i.e. high-information tokens).

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

Usually

-1.22

？！”

-1.13

 because

-1.06

and

-1.06

Obviously

-1.05

 väljer

-1.05

Essentially

-1.01

 blatantly

-1.01

Since

-1.00

のお店

-0.99

POSITIVE LOGITS

 commerciaux

1.04

では

0.97

 afbeelding

0.95



0.95

 события

0.93

 женщины

0.92

 动漫

0.91

ㅣ

0.91

 zonne

0.91

污

0.91

Activations Density 0.082%

biomarker proteins

technical or specialized terms within academic, mathematical, or technical contexts.

The neuron responds to relatively rare or content-rich words (i.e. high-information tokens).

No Comments

No Known Activations

biomarker proteins

technical or specialized terms within academic, mathematical, or technical contexts.

The neuron responds to relatively rare or content-rich words (i.e. high-information tokens).

No Comments

No Known Activations