INDEX

Explanations

ovarian cancer

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

references to ovarian cancer in medical literature.

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

The neuron strongly activates on mentions of “ovarian” (especially in the context of ovarian cancer).

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

Negative Logits

-2.59

ING

-2.59

autaire

-2.56

 kaos

-2.36

which

-2.36

揠

-2.31

 sierp

-2.23

媜

-2.20

 装着

-2.20

 بيان

-2.19

POSITIVE LOGITS

↵↵

3.53

</strong>

2.28

1.98

 meddling

1.97

—

1.92

1.88

и

1.84

seu

1.84

 rescuing

1.84

be

1.80

Activations Density 0.013%

ovarian cancer

references to ovarian cancer in medical literature.

The neuron strongly activates on mentions of “ovarian” (especially in the context of ovarian cancer).

No Known Activations

ovarian cancer

references to ovarian cancer in medical literature.

The neuron strongly activates on mentions of “ovarian” (especially in the context of ovarian cancer).

No Known Activations