INDEX

Explanations

GGT activity

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

abbreviations or acronyms in technical, scientific, or legal contexts.

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

The neuron fires on Chinese degree or quantity words that add emphasis (e.g. “很,” “很多,” “像”).

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

شكرا

-2.61

牁

-2.39

櫪

-2.30

⸨

-2.28

৹

-2.27

edere

-2.25

 コットン

-2.22

bundet

-2.19

 OFFICES

-2.14

POSITIVE LOGITS

—

2.47

that

2.17

2.13

vantaged

2.13

("

2.11

?’

2.08

 schöne

2.08

л

2.06

2.05

鏖

2.05

Activations Density 0.000%

GGT activity

abbreviations or acronyms in technical, scientific, or legal contexts.

The neuron fires on Chinese degree or quantity words that add emphasis (e.g. “很,” “很多,” “像”).

No Comments

No Known Activations

GGT activity

abbreviations or acronyms in technical, scientific, or legal contexts.

The neuron fires on Chinese degree or quantity words that add emphasis (e.g. “很,” “很多,” “像”).

No Comments

No Known Activations