INDEX

Explanations

first-generation immigrants

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

The neuron fires on words that mark ordinal status or under‐represented group labels—e.g. “first,” “second,” “underserved,” “minority.”

oai_token-act-pair · o4-mini

Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_34/width_131k

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

桝

-0.75

ровок

-0.75

人在

-0.72

 Adrien

-0.71

로운

-0.70

 Address

-0.70

 setAddress

-0.69

="./

-0.69

在中国

-0.69

batross

-0.68

POSITIVE LOGITS

 first

3.61

first

2.97

 First

2.73

First

2.72

 první

2.44

 FIRST

2.34

 eerste

2.17

FIRST

2.11

 ﬁrst

2.09

 ersten

2.02

Activations Density 0.014%

first-generation immigrants

The neuron fires on words that mark ordinal status or under‐represented group labels—e.g. “first,” “second,” “underserved,” “minority.”

No Known Activations

first-generation immigrants

The neuron fires on words that mark ordinal status or under‐represented group labels—e.g. “first,” “second,” “underserved,” “minority.”

No Known Activations

first-generation immigrants

The neuron fires on words that mark ordinal status or under‐represented group labels—e.g. “first,” “second,” “under­served,” “minority.”

No Known Activations

first-generation immigrants

The neuron fires on words that mark ordinal status or under‐represented group labels—e.g. “first,” “second,” “under­served,” “minority.”

No Known Activations

The neuron fires on words that mark ordinal status or under‐represented group labels—e.g. “first,” “second,” “underserved,” “minority.”

The neuron fires on words that mark ordinal status or under‐represented group labels—e.g. “first,” “second,” “underserved,” “minority.”