INDEX

Explanations

biological research

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

specialized technical terms in computer science and biology.

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

The neuron fires on multi-syllabic technical or scientific jargon—especially tokens ending in recognizable model, function, or classification suffixes like “‐max,” “-bit,” “-omics,” or “-ocytes.”

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

tazione

-2.34

%;

-2.20

逦

-2.19

-2.11

鶺

-2.08

姈

-2.06

 ellos

-2.05

 xxiv

-2.03

 сист

-1.99

orsese

-1.98

POSITIVE LOGITS

We

2.03

啖

1.92

It

1.91

꽤

1.89

1.88

当

1.88



1.88

 expérimentés

1.87

1.85

嬉しいです

1.84

Activations Density 0.000%

biological research

specialized technical terms in computer science and biology.

The neuron fires on multi-syllabic technical or scientific jargon—especially tokens ending in recognizable model, function, or classification suffixes like “‐max,” “-bit,” “-omics,” or “-ocytes.”

No Comments

No Known Activations

biological research

specialized technical terms in computer science and biology.

The neuron fires on multi-syllabic technical or scientific jargon—especially tokens ending in recognizable model, function, or classification suffixes like “‐max,” “-bit,” “-omics,” or “-ocytes.”

No Comments

No Known Activations