INDEX

Explanations

bottom line

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

The neuron activates on occurrences of the word “bottom” (including compounds like “bottom-line” or “bottoming”).

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

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_34/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

 waypoint

-0.78

reden

-0.77

 pequeno

-0.77

 goofy

-0.77

taja

-0.76

思议

-0.76

骉

-0.76

 thri

-0.75

mesan

-0.75

长

-0.75

POSITIVE LOGITS

 line

1.93

line

1.52

 bottom

1.33

 Line

1.24

Line

1.23

LINE

1.05

ライン

1.01

 ligne

0.99

 línea

0.98

getLine

0.95

Activations Density 0.010%

bottom line

The neuron activates on occurrences of the word “bottom” (including compounds like “bottom-line” or “bottoming”).

No Comments

No Known Activations

bottom line

The neuron activates on occurrences of the word “bottom” (including compounds like “bottom-line” or “bottoming”).

No Comments

No Known Activations

bottom line

The neuron activates on occurrences of the word “bottom” (including compounds like “bottom-​line” or “bottoming”).

No Comments

No Known Activations

bottom line

The neuron activates on occurrences of the word “bottom” (including compounds like “bottom-​line” or “bottoming”).

No Comments

No Known Activations

The neuron activates on occurrences of the word “bottom” (including compounds like “bottom-line” or “bottoming”).

The neuron activates on occurrences of the word “bottom” (including compounds like “bottom-line” or “bottoming”).