INDEX

Explanations

scientific models

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

references to animal research models, particularly mouse or murine models in scientific papers.

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

The neuron flags references to experimental models or paradigms (e.g. “mouse model,” “animal model,” “murine model,” “system,” “paradigm”) in biomedical 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

-1.67

le

-1.59

ra

-1.45

ina

-1.42

ado

-1.39

</h5>

-1.38

ㅂ

-1.38

ㅌ

-1.36

ver

-1.34

ousness

-1.34

POSITIVE LOGITS

вість

1.58

quirer

1.55

of

1.55

늦

1.55

芘

1.54

 минуту

1.48

我們

1.41

 toujours

1.39

いつでも

1.36

chiai

1.35

Activations Density 0.174%

scientific models

references to animal research models, particularly mouse or murine models in scientific papers.

The neuron flags references to experimental models or paradigms (e.g. “mouse model,” “animal model,” “murine model,” “system,” “paradigm”) in biomedical text.

No Comments

No Known Activations

scientific models

references to animal research models, particularly mouse or murine models in scientific papers.

The neuron flags references to experimental models or paradigms (e.g. “mouse model,” “animal model,” “murine model,” “system,” “paradigm”) in biomedical text.

No Comments

No Known Activations