INDEX

Explanations

protection from, of, or against

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

The neuron activates for the word "Protection" especially when used in contexts of safeguarding, security, or defense mechanisms.

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

The main thing this neuron does is detect occurrences of the word stem “protect” (e.g. “protection,” “protecting,” “protect”).

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

of

-2.67

！"

-2.63

ᵴ

-2.53

 économie

-2.41

💮

-2.39

 apparence

-2.34

蹋

-2.28

-2.27

壜

-2.27



-2.25

POSITIVE LOGITS

”,

3.05

of

3.00

↵

2.94

”:

2.94

2.91

):

2.86

’)

2.83

 durch

2.81

’,

2.69

”;

2.67

Activations Density 0.024%

protection from, of, or against

The neuron activates for the word "Protection" especially when used in contexts of safeguarding, security, or defense mechanisms.

The main thing this neuron does is detect occurrences of the word stem “protect” (e.g. “protection,” “protecting,” “protect”).

No Comments

No Known Activations

protection from, of, or against

The neuron activates for the word "Protection" especially when used in contexts of safeguarding, security, or defense mechanisms.

The main thing this neuron does is detect occurrences of the word stem “protect” (e.g. “protection,” “protecting,” “protect”).

No Comments

No Known Activations