INDEX

Explanations

medical devices

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

technical or medical terms in scientific or academic texts.

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

The neuron fires on words that are parts of hyphenated or compound technical terms (e.g. the components of “Y-stent-assisted,” “neck-aneurysm,” or “event-related fMRI”).

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

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

it

-1.51

 their

-1.07

Vorlage

-1.03

zkiem

-1.03

жаю

-1.00

'/>

-0.99

—¿

-0.99

 необхідно

-0.98

squareup

-0.97

optarg

-0.96

POSITIVE LOGITS

vs

1.22

 muitas

1.10

and

1.02

 vexed

1.02

 wilden

1.01

 souvent

0.99

 muitos

0.98

 versus

0.96

often

0.94

 veya

0.94

Activations Density 0.114%

medical devices

technical or medical terms in scientific or academic texts.

The neuron fires on words that are parts of hyphenated or compound technical terms (e.g. the components of “Y-stent-assisted,” “neck-aneurysm,” or “event-related fMRI”).

No Comments

No Known Activations

medical devices

technical or medical terms in scientific or academic texts.

The neuron fires on words that are parts of hyphenated or compound technical terms (e.g. the components of “Y-stent-assisted,” “neck-aneurysm,” or “event-related fMRI”).

No Comments

No Known Activations