INDEX

Explanations

Rho family GTPases

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

references to "Rho" proteins or compounds in scientific and technical contexts.

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

The neuron specifically detects the occurrence of the token “Rho” (the Rho protein name) in text.

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

縂

-2.81

 juft

-2.55

 також

-2.55

 вона

-2.47

?”

-2.45

 Pristup

-2.45

裃

-2.41

 alamy

-2.39

 chofe

-2.38

縢

-2.36

POSITIVE LOGITS

2.83

2.39

2.33

ๆ

2.31

考生

2.14

 fille

2.13

ଢ

2.11

2.09

—

2.08

Activations Density 0.003%

Rho family GTPases

references to "Rho" proteins or compounds in scientific and technical contexts.

The neuron specifically detects the occurrence of the token “Rho” (the Rho protein name) in text.

No Comments

No Known Activations

Rho family GTPases

references to "Rho" proteins or compounds in scientific and technical contexts.

The neuron specifically detects the occurrence of the token “Rho” (the Rho protein name) in text.

No Comments

No Known Activations