INDEX

Explanations

The neuron fires on highly technical scientific parameter and measurement terms (e.g. “small,” “momenta,” “relaxation,” “thermal,” “QCD,” single‐letter variables like “D,” etc.).

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

scientific observation

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

scientific and technical terminology in academic research papers.

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

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

 revamped

-1.24

 astounding

-1.17

 momentous

-1.16

 colecciones

-1.15

 quirky

-1.15

 startling

-1.14

 distinctive

-1.13

 strikingly

-1.12

 gigantic

-1.10

 empfohlen

-1.09

POSITIVE LOGITS

 which

1.41

 where

1.37

 this

1.29

one

1.23

or

1.17

 before

1.16

၅

1.13

🤧

1.06

🎉

1.05

 Before

1.04

Activations Density 0.149%

The neuron fires on highly technical scientific parameter and measurement terms (e.g. “small,” “momenta,” “relaxation,” “thermal,” “QCD,” single‐letter variables like “D,” etc.).

scientific observation

scientific and technical terminology in academic research papers.

No Comments

No Known Activations

The neuron fires on highly technical scientific parameter and measurement terms (e.g. “small,” “momenta,” “relaxation,” “thermal,” “QCD,” single‐letter variables like “D,” etc.).

scientific observation

scientific and technical terminology in academic research papers.

No Comments

No Known Activations