INDEX

Explanations

PF acronyms

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

the abbreviation "PF" (often as part of technical or scientific terms).

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

The neuron responds to occurrences of the letters “PF” (in any case), i.e. the “PF” acronym or token.

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

齪

-3.00

that

-2.64

骉

-2.42

-2.39

 unmittel

-2.27

The

-2.25

皺

-2.25

ні

-2.23

)$,

-2.20

POSITIVE LOGITS

鮡

3.00

﹕

2.67

 手绘

2.58

櫚

2.53

錀

2.52

 ciment

2.48

榈

2.48

岁的

2.44

筇

2.42

に来

2.41

Activations Density 0.004%

PF acronyms

the abbreviation "PF" (often as part of technical or scientific terms).

The neuron responds to occurrences of the letters “PF” (in any case), i.e. the “PF” acronym or token.

No Comments

No Known Activations

PF acronyms

the abbreviation "PF" (often as part of technical or scientific terms).

The neuron responds to occurrences of the letters “PF” (in any case), i.e. the “PF” acronym or token.

No Comments

No Known Activations