INDEX

Explanations

code parsing and syntax

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

commas that separate function or method arguments in code.

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

The neuron fires on numeric literal tokens (numbers and numeric constants) in the code.

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

-1.93

 первым

-1.84

鋮

-1.77

𝟏

-1.66

’

-1.64

帝

-1.62

珖

-1.58

なんと

-1.56

甗

-1.56

POSITIVE LOGITS

噐

2.19

 protože

2.17

 responsabile

2.13

 количества

1.96

are

1.94

 abbiamo

1.94

不

1.92

ズニー

1.92

 crescente

1.91

تیجه

1.90

Activations Density 0.044%

code parsing and syntax

commas that separate function or method arguments in code.

The neuron fires on numeric literal tokens (numbers and numeric constants) in the code.

No Comments

No Known Activations

code parsing and syntax

commas that separate function or method arguments in code.

The neuron fires on numeric literal tokens (numbers and numeric constants) in the code.

No Comments

No Known Activations