INDEX

Explanations

patient groups

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

mentions of patient groups or populations in medical/scientific research contexts.

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

The neuron fires on terms marking study or patient cohorts—words that indicate groups of subjects (e.g. “group,” “patients,” “groups”) in clinical‐study contexts.

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

 suchte

-1.52

 нам

-1.49

They

-1.47

CCIÓN

-1.34

鲥

-1.33

imental

-1.29

neling

-1.28

nival

-1.27

amaran

-1.27

it

-1.27

POSITIVE LOGITS

 kemudian

1.88

of

1.63

 siendo

1.58

 then

1.56

については

1.55

]);

1.54

"]="

1.53

⚋

1.53

 when

1.52

 difficulté

1.51

Activations Density 0.082%

patient groups

mentions of patient groups or populations in medical/scientific research contexts.

The neuron fires on terms marking study or patient cohorts—words that indicate groups of subjects (e.g. “group,” “patients,” “groups”) in clinical‐study contexts.

No Comments

No Known Activations

patient groups

mentions of patient groups or populations in medical/scientific research contexts.

The neuron fires on terms marking study or patient cohorts—words that indicate groups of subjects (e.g. “group,” “patients,” “groups”) in clinical‐study contexts.

No Comments

No Known Activations