INDEX

Explanations

data science, analysis, analytics

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

references to data science, data analysis, and related technical professions or fields.

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

The neuron fires strongly on the word “data” (especially when it appears in titles or roles like “data scientist,” “data science,” or “data analytics”).

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



-1.64

 bañ

-1.55

wieś

-1.46

 razie

-1.45

各有

-1.44

焄

-1.43

瑨

-1.41

 wykonane

-1.41

 them

-1.40

 nedeniyle

-1.40

POSITIVE LOGITS

ю

1.65

1.61

1.55

1.54

ent

1.53

//

1.50

1.48

1.45

ir

1.44

IL

1.42

Activations Density 0.035%

data science, analysis, analytics

references to data science, data analysis, and related technical professions or fields.

The neuron fires strongly on the word “data” (especially when it appears in titles or roles like “data scientist,” “data science,” or “data analytics”).

No Comments

No Known Activations

data science, analysis, analytics

references to data science, data analysis, and related technical professions or fields.

The neuron fires strongly on the word “data” (especially when it appears in titles or roles like “data scientist,” “data science,” or “data analytics”).

No Comments

No Known Activations