INDEX

Explanations

clinical trial and study

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

scientific or medical studies and research papers.

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

The neuron activates on terms naming research study designs or clinical trial descriptors (e.g. “trial,” “study,” “cohort,” “case-control,” “randomized,” etc.).

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

}}

-1.73

 originalen

-1.64

鹮

-1.63

ቍ

-1.62

 festen

-1.56

 itinéraire

-1.55

偸

-1.53

istischen

-1.46



-1.46

 protože

-1.45

POSITIVE LOGITS

and

1.52

ss

1.43

母の

1.41

not

1.39

or

1.39

就是一个

1.37

 وو

1.36

1.35

 Vaters

1.34

 botines

1.27

Activations Density 0.871%

clinical trial and study

scientific or medical studies and research papers.

The neuron activates on terms naming research study designs or clinical trial descriptors (e.g. “trial,” “study,” “cohort,” “case-control,” “randomized,” etc.).

No Comments

No Known Activations

clinical trial and study

scientific or medical studies and research papers.

The neuron activates on terms naming research study designs or clinical trial descriptors (e.g. “trial,” “study,” “cohort,” “case-control,” “randomized,” etc.).

No Comments

No Known Activations