INDEX

Explanations

gas and gasoline

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

mentions of gasoline or fuel, especially in the context of vehicles or engines.

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

The neuron activates on mentions of different fuel types (e.g. gasoline, diesel, kerosene).

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

 eſſ

-2.34



-1.97

est

-1.96

-1.84

 octavia

-1.75

 perched

-1.69

 estadounidense

-1.68

 embodied

-1.68

 dressed

-1.67

-1.66

POSITIVE LOGITS

ть

1.93

 memutus

1.80

気持ちを

1.74

 únicas

1.70

 Когда

1.70

iteľ

1.68

 surges

1.68

 stehenden

1.67

楽しみに

1.66

 [''],

1.66

Activations Density 0.011%

gas and gasoline

mentions of gasoline or fuel, especially in the context of vehicles or engines.

The neuron activates on mentions of different fuel types (e.g. gasoline, diesel, kerosene).

No Comments

No Known Activations

gas and gasoline

mentions of gasoline or fuel, especially in the context of vehicles or engines.

The neuron activates on mentions of different fuel types (e.g. gasoline, diesel, kerosene).

No Comments

No Known Activations