INDEX

Explanations

grasses and cereals

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

plant names, especially grasses and botanical species.

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

Triggered by @neilrathi

The neuron is detecting scientific taxonomic names (especially Latin genus and species names) in the 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

Negative Logits

in

-1.58

遄

-1.54

 другая

-1.51

part

-1.41

these

-1.40

("

-1.38

、「

-1.36

籥

-1.35

—"

-1.33

ystis

-1.32

POSITIVE LOGITS

是最

1.41

囑

1.40

），

1.36

是我们

1.34

 seperti

1.30

덥

1.30

쌤

1.29

 tutors

1.26

 gets

1.24

关系

1.23

Activations Density 0.049%

grasses and cereals

plant names, especially grasses and botanical species.

The neuron is detecting scientific taxonomic names (especially Latin genus and species names) in the text.

No Known Activations

grasses and cereals

plant names, especially grasses and botanical species.

The neuron is detecting scientific taxonomic names (especially Latin genus and species names) in the text.

No Known Activations