INDEX

Explanations

named entities and medical terms

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

proper nouns representing people or locations, particularly names like "Damon," "Saratoga," and "Villanova."

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

The neuron is triggered by named entities—that is, proper nouns such as personal names (e.g. “Damon”), place names (“Saratoga”), species names (“crickets”), or other titled terms.

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

絝

-3.25

灕

-2.78

姉

-2.64

鲻

-2.64

 femeninos

-2.56

㑹

-2.52

 capucha

-2.50

 bús

-2.47

皤

-2.47

࿊

-2.42

POSITIVE LOGITS

2.92

नलोड

2.55

un

2.52

,”

2.50

ндарт

2.48

2.47

2.44

2.39

Activations Density 0.022%

named entities and medical terms

proper nouns representing people or locations, particularly names like "Damon," "Saratoga," and "Villanova."

The neuron is triggered by named entities—that is, proper nouns such as personal names (e.g. “Damon”), place names (“Saratoga”), species names (“crickets”), or other titled terms.

No Comments

No Known Activations

named entities and medical terms

proper nouns representing people or locations, particularly names like "Damon," "Saratoga," and "Villanova."

The neuron is triggered by named entities—that is, proper nouns such as personal names (e.g. “Damon”), place names (“Saratoga”), species names (“crickets”), or other titled terms.

No Comments

No Known Activations