INDEX

Explanations

medical and scientific terms

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

medical terms for body parts and anatomical structures.

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

The neuron fires on long, multi-syllable tokens—especially specialized technical or scientific terms (e.g. biomedical jargon or other domain-specific vocabulary).

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

 alpes

-1.25

 vernis

-1.19

 vín

-1.19

 dél

-1.19

 pán

-1.19

 stratég

-1.19

espół

-1.19

 ailes

-1.18

Ikr

-1.18

 arbre

-1.16

POSITIVE LOGITS

1.30

1.29

1.26

1.23

1.19

To

1.18

1.17

1.16

Activations Density 0.272%

medical and scientific terms

medical terms for body parts and anatomical structures.

The neuron fires on long, multi-syllable tokens—especially specialized technical or scientific terms (e.g. biomedical jargon or other domain-specific vocabulary).

No Comments

No Known Activations

medical and scientific terms

medical terms for body parts and anatomical structures.

The neuron fires on long, multi-syllable tokens—especially specialized technical or scientific terms (e.g. biomedical jargon or other domain-specific vocabulary).

No Comments

No Known Activations