INDEX

Explanations

complying, compiling, complain

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

the token "Comp" when it appears as part of words like "Compiling", "Complain", "Compiz", or "Compounds".

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

The neuron is keyed to any token beginning with the letters “Comp,” such as the start of words like “Compiling,” “Computer,” or “Compounds.”

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

 Their

-3.19

 Heilige

-2.88

 worin

-2.50

鴣

-2.44

 womit

-2.44

蹰

-2.42

 รวม

-2.38

畯

-2.38

生死

-2.36

金钱

-2.34

POSITIVE LOGITS

the

3.73

3.55

3.48

3.39

3.03

2.95

2.91

進入

2.84

2.67

錶

2.61

Activations Density 0.019%

complying, compiling, complain

the token "Comp" when it appears as part of words like "Compiling", "Complain", "Compiz", or "Compounds".

The neuron is keyed to any token beginning with the letters “Comp,” such as the start of words like “Compiling,” “Computer,” or “Compounds.”

No Comments

No Known Activations

complying, compiling, complain

the token "Comp" when it appears as part of words like "Compiling", "Complain", "Compiz", or "Compounds".

The neuron is keyed to any token beginning with the letters “Comp,” such as the start of words like “Compiling,” “Computer,” or “Compounds.”

No Comments

No Known Activations