INDEX

Explanations

genetic mutation

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

references to genetic mutations in scientific or medical contexts.

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

The main thing this neuron does is spot occurrences of “mutation” (and its grammatical variants).

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

蕺

-2.44

</h3>

-2.42

☑️

-2.31

 plantes

-2.28

💁

-2.22

warzys

-2.22

ться

-2.19

 dezelve

-2.16

uly

-2.16

dienne

-2.16

POSITIVE LOGITS

↵

3.81

</b>

2.97

࣭

2.38

 másik

2.23

<i>

2.17

之类的

2.11

2.05

もや

2.02

什么的

2.00

ǌ

1.99

Activations Density 0.023%

genetic mutation

references to genetic mutations in scientific or medical contexts.

The main thing this neuron does is spot occurrences of “mutation” (and its grammatical variants).

No Comments

No Known Activations

genetic mutation

references to genetic mutations in scientific or medical contexts.

The main thing this neuron does is spot occurrences of “mutation” (and its grammatical variants).

No Comments

No Known Activations