INDEX

Explanations

medical acronyms

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

medical and clinical abbreviations or acronyms.

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

The neuron activates on uppercase acronym or initialism tokens (short sequences of capital letters).

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

 these

-1.54

Андрей

-1.32

Ehrungen

-1.30

its

-1.27

 elástico

-1.26

Олег

-1.25

Also

-1.23

 regulador

-1.23

當時

-1.22

實際

-1.21

POSITIVE LOGITS

cún

1.23

rungsseite

1.16

 febrero

1.15



1.14

']->

1.13

often

1.12

fattning

1.11

뿍

1.11

)=\

1.11

}$.

1.11

Activations Density 0.771%

medical acronyms

medical and clinical abbreviations or acronyms.

The neuron activates on uppercase acronym or initialism tokens (short sequences of capital letters).

No Comments

No Known Activations

medical acronyms

medical and clinical abbreviations or acronyms.

The neuron activates on uppercase acronym or initialism tokens (short sequences of capital letters).

No Comments

No Known Activations