INDEX

Explanations

violation, COOH, cows, bin

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

technical syntax and notation in programming, mathematics, and scientific contexts.

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

The neuron is primarily triggered by numeric tokens (digits and numbers) in the text.

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

据说

-1.06

 Estou

-0.96

 voila

-0.92

 ergän

-0.91

 peut

-0.91

 것이다

-0.89

 lauded

-0.88

是一款

-0.88

存款

-0.88

夠

-0.87

POSITIVE LOGITS



1.02

While

0.99

}:{

0.97

وكان

0.96

 with

0.93

 through

0.92

 before

0.90

 while

0.89

vábbi

0.88

Your

0.87

Activations Density 0.046%

violation, COOH, cows, bin

technical syntax and notation in programming, mathematics, and scientific contexts.

The neuron is primarily triggered by numeric tokens (digits and numbers) in the text.

No Comments

No Known Activations

violation, COOH, cows, bin

technical syntax and notation in programming, mathematics, and scientific contexts.

The neuron is primarily triggered by numeric tokens (digits and numbers) in the text.

No Comments

No Known Activations