INDEX

Explanations

micro followed by somal, surgery, service, satellite, or services

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

The neuron detects the term "microsomal" and related "micro" technical terms in scientific and programming contexts.

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

The neuron fires on the character sequence “micros,” i.e. tokens beginning with the “micro(s)-” prefix.

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

Negative Logits

-2.75

-2.67

ا

-2.63

ان

-2.55

-2.33

са

-2.22

ма

-2.14

谞

-2.08

-2.06

able

-2.02

POSITIVE LOGITS

喼

2.83



2.81



2.80

謦

2.67

 δεν

2.56

劼

2.53

 estekak

2.48

Зно

2.45

derdag

2.44



2.39

Activations Density 0.002%

micro followed by somal, surgery, service, satellite, or services

The neuron detects the term "microsomal" and related "micro" technical terms in scientific and programming contexts.

The neuron fires on the character sequence “micros,” i.e. tokens beginning with the “micro(s)-” prefix.

No Known Activations

micro followed by somal, surgery, service, satellite, or services

The neuron detects the term "microsomal" and related "micro" technical terms in scientific and programming contexts.

The neuron fires on the character sequence “micros,” i.e. tokens beginning with the “micro(s)-” prefix.

No Known Activations