INDEX

Explanations

scientific and clinical findings

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

scientific terms related to patterns, effects, and functions in technical or academic contexts.

oai_token-act-pair · claude-3-7-sonnet-20250219 Triggered by @neilrathi

The neuron strongly activates on technical scientific or engineering–style nouns—particularly domain-specific jargon for methods, measurements, properties, and phenomena.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/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

 erbjud

-1.45

很赞

-1.37

 lyck

-1.30

 väldigt

-1.30

Maintenant

-1.28

 föres

-1.27

 anvä

-1.27

 äls

-1.27

but

-1.24

Afin

-1.24

POSITIVE LOGITS

 across

1.37

in

1.37

 bijvoorbeeld

1.30

and

1.19

 бампер

1.12

at

1.09

of

1.09

 весна

1.03

 einschließlich

1.02

 from

0.99

Activations Density 0.119%

scientific and clinical findings

scientific terms related to patterns, effects, and functions in technical or academic contexts.

The neuron strongly activates on technical scientific or engineering–style nouns—particularly domain-specific jargon for methods, measurements, properties, and phenomena.

No Comments

No Known Activations

scientific and clinical findings

scientific terms related to patterns, effects, and functions in technical or academic contexts.

The neuron strongly activates on technical scientific or engineering–style nouns—particularly domain-specific jargon for methods, measurements, properties, and phenomena.

No Comments

No Known Activations