INDEX

Explanations

anterior anatomical locations

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

The neuron detects the anatomical term "anterior" in medical contexts.

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

The neuron detects anatomical directional terms (e.g., “anterior,” “posterior”) 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

-2.66

-2.63

The

-2.59

’

-2.47

-2.44

いだ

-2.44

-2.34

-2.23

’:

-2.22

We

-2.17

POSITIVE LOGITS

幾天

2.83

髏

2.81

most

2.75

ୌ

2.63

 москва

2.61

↵

2.59

ICOLON

2.55

፨

2.55

 prioritizing

2.53

ᚺ

2.53

Activations Density 0.008%

anterior anatomical locations

The neuron detects the anatomical term "anterior" in medical contexts.

The neuron detects anatomical directional terms (e.g., “anterior,” “posterior”) in biomedical text.

No Comments

No Known Activations

anterior anatomical locations

The neuron detects the anatomical term "anterior" in medical contexts.

The neuron detects anatomical directional terms (e.g., “anterior,” “posterior”) in biomedical text.

No Comments

No Known Activations