INDEX

Explanations

SCFA, SL, SN, abbreviations

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

abbreviations and technical acronyms, especially those related to computing and scientific terminology.

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

The neuron is primarily detecting multi‐letter uppercase abbreviations or acronyms (e.g. SI, SR, SN, SCF, TNBS, NIR) in technical/scientific or code contexts.

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

Negative Logits

⁛

-2.23

が見えて

-2.22

 ücretsiz

-2.16

描いた

-2.09

 všem

-2.05

 formatos

-2.05

 Would

-2.03

描く

-2.02

Estamos

-2.00

 barvy

-2.00

POSITIVE LOGITS

ed

2.75

that

2.69

et

2.66

2.59

",

2.48

,“

2.48

2.45

2.44

具有

2.42

this

2.39

Activations Density 6.763%

SCFA, SL, SN, abbreviations

abbreviations and technical acronyms, especially those related to computing and scientific terminology.

The neuron is primarily detecting multi‐letter uppercase abbreviations or acronyms (e.g. SI, SR, SN, SCF, TNBS, NIR) in technical/scientific or code contexts.

No Known Activations

SCFA, SL, SN, abbreviations

abbreviations and technical acronyms, especially those related to computing and scientific terminology.

The neuron is primarily detecting multi‐letter uppercase abbreviations or acronyms (e.g. SI, SR, SN, SCF, TNBS, NIR) in technical/scientific or code contexts.

No Known Activations