INDEX

Explanations

Aussie Icon, Pseudomonas aeruginosa strains

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

The neuron detects references to Australian terms and organisms (particularly "Aussie" and "Pseudomonas aeruginosa").

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

The neuron fires on uncommon proper nouns—specifically demonyms (e.g. “Aussie”) and scientific species epithets (e.g. “aeruginosa”).

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

-2.75

潆

-2.59

趼

-2.58

巨大的

-2.47



-2.45

鸶

-2.45

大家的

-2.44

蔔

-2.39

 كيفية

-2.38

不明白

-2.36

POSITIVE LOGITS

 Also

2.47

ном

2.31

and

2.17

has

2.17

ні

2.13

We

2.09

и

2.02

 happened

2.00

was

1.98

 роза

1.96

Activations Density 0.001%

Aussie Icon, Pseudomonas aeruginosa strains

The neuron detects references to Australian terms and organisms (particularly "Aussie" and "Pseudomonas aeruginosa").

The neuron fires on uncommon proper nouns—specifically demonyms (e.g. “Aussie”) and scientific species epithets (e.g. “aeruginosa”).

No Comments

No Known Activations

Aussie Icon, Pseudomonas aeruginosa strains

The neuron detects references to Australian terms and organisms (particularly "Aussie" and "Pseudomonas aeruginosa").

The neuron fires on uncommon proper nouns—specifically demonyms (e.g. “Aussie”) and scientific species epithets (e.g. “aeruginosa”).

No Comments

No Known Activations