INDEX

Explanations

code comments and definitions

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

periods that end sentences in comments or documentation within source code.

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

This neuron fires on descriptive comment text in code (e.g. sentences in comments or docstrings explaining functionality).

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

-2.14

是

-2.02

 должен

-2.02

.....

-1.98

«

-1.95

Конечно

-1.81

 &___

-1.80

 Ganzen

-1.76

 proverbial

-1.73

......

-1.73

POSITIVE LOGITS

荇

2.09

 tega

2.05

𓏸

2.03

脔

2.02

nji

2.02

稣

2.00

 हालांकि

1.88

tieron

1.87

vailability

1.87

.");

1.85

Activations Density 0.481%

code comments and definitions

periods that end sentences in comments or documentation within source code.

This neuron fires on descriptive comment text in code (e.g. sentences in comments or docstrings explaining functionality).

No Comments

No Known Activations

code comments and definitions

periods that end sentences in comments or documentation within source code.

This neuron fires on descriptive comment text in code (e.g. sentences in comments or docstrings explaining functionality).

No Comments

No Known Activations