INDEX

Explanations

pump, pumping, pumped

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

references to pumping or pump-related actions.

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

Triggered by @neilrathi

The main thing this neuron does is detect the word “pump” (in its various forms like pumping, pumped, pumps).

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

and

-2.58

-2.48

-2.47

-2.23

-2.22

但

-2.20

The

-2.16

但在

-2.09

-2.06

-1.99

POSITIVE LOGITS

 είναι

2.56

珝

2.25

𐑂

2.14

还真是

2.05

Pump

2.05

iſe

2.03

2.02

∽

2.00

 Diputados

1.98

身边的

1.94

Activations Density 0.009%

pump, pumping, pumped

references to pumping or pump-related actions.

The main thing this neuron does is detect the word “pump” (in its various forms like pumping, pumped, pumps).

No Known Activations

pump, pumping, pumped

references to pumping or pump-related actions.

The main thing this neuron does is detect the word “pump” (in its various forms like pumping, pumped, pumps).

No Known Activations