INDEX

Explanations

grass

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

references to grass and lawn-related terms.

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

The neuron strongly activates on occurrences of “grass” (including compounds like “grassland”) and thus detects mentions of grass.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/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

?’

-3.00

僂

-2.58

彀

-2.52

餿

-2.39

銪

-2.23

もう一度

-2.23

’?

-2.23

豋

-2.22

スポンサーリンク

-2.20

⦆

-2.17

POSITIVE LOGITS

2.42

ዡ

2.17

га

2.16

，

2.09

鸝

2.02

1.99

不宜

1.99

！”

1.99

 отвечает

1.97

的

1.96

Activations Density 0.007%

grass

references to grass and lawn-related terms.

The neuron strongly activates on occurrences of “grass” (including compounds like “grassland”) and thus detects mentions of grass.

No Comments

No Known Activations

grass

references to grass and lawn-related terms.

The neuron strongly activates on occurrences of “grass” (including compounds like “grassland”) and thus detects mentions of grass.

No Comments

No Known Activations