INDEX

Explanations

mammogram mamal mammary

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

The neuron detects the word stem "Mam" at the beginning of words like "Mammography," "Mammals," "Mambo," and "Mamzer."

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

The neuron fires on fragments of the word “mammography” (e.g. “mammo,” “mammography,” 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

 ส์

-2.80

鼕

-2.78

妡

-2.69

panjang

-2.67

铪

-2.59

蕖

-2.56

啬

-2.56

蚡

-2.55

ingtones

-2.53

毉

-2.45

POSITIVE LOGITS

’

3.69

3.09

2.88

2.84

IS

2.81

 excruciating

2.78

2.77

2.59

2.56

</h2>

2.53

Activations Density 0.004%

mammogram mamal mammary

The neuron detects the word stem "Mam" at the beginning of words like "Mammography," "Mammals," "Mambo," and "Mamzer."

The neuron fires on fragments of the word “mammography” (e.g. “mammo,” “mammography,” etc.).

No Comments

No Known Activations

mammogram mamal mammary

The neuron detects the word stem "Mam" at the beginning of words like "Mammography," "Mammals," "Mambo," and "Mamzer."

The neuron fires on fragments of the word “mammography” (e.g. “mammo,” “mammography,” etc.).

No Comments

No Known Activations