INDEX

Explanations

medical imaging and scientific suffixes

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

scientific and technical terminology, especially in medical and chemical contexts.

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

The neuron strongly activates on the very first token of a sentence (typically a capitalized or standalone word).

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

 trám

-2.55

are

-2.44

 originalen

-2.39

to

-2.27

guigu

-2.19

 žiad

-2.19

lenovo

-2.17

lxt

-2.11

 čern

-2.08

 sám

-2.06

POSITIVE LOGITS

it

2.58

if

2.48

when

2.19

 when

2.19

 after

2.05

 this

2.03

(*´

2.00

 because

1.97

the

1.96

as

1.92

Activations Density 0.103%

medical imaging and scientific suffixes

scientific and technical terminology, especially in medical and chemical contexts.

The neuron strongly activates on the very first token of a sentence (typically a capitalized or standalone word).

No Comments

No Known Activations

medical imaging and scientific suffixes

scientific and technical terminology, especially in medical and chemical contexts.

The neuron strongly activates on the very first token of a sentence (typically a capitalized or standalone word).

No Comments

No Known Activations