INDEX

Explanations

seeds, grains, and kernels

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

references to grains, especially in agricultural or scientific contexts.

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

Triggered by @neilrathi

The neuron activates on occurrences of the word “grain” (and its plural “grains”).

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

-1.77

is

-1.63

ed

-1.45

 ayakkab

-1.42

 rampant

-1.41

art

-1.35

as

-1.34

lev

-1.34

me

-1.33

he

-1.32

POSITIVE LOGITS

葑

1.56

 Когда

1.48

ukraine

1.43

︺

1.40

(*.

1.39

tabPage

1.39

ʬ

1.38

 будут

1.34

zembro

1.32

ARROLLO

1.32

Activations Density 0.089%

seeds, grains, and kernels

references to grains, especially in agricultural or scientific contexts.

The neuron activates on occurrences of the word “grain” (and its plural “grains”).

No Known Activations

seeds, grains, and kernels

references to grains, especially in agricultural or scientific contexts.

The neuron activates on occurrences of the word “grain” (and its plural “grains”).

No Known Activations