INDEX

Explanations

glomerular disease

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

This neuron detects words or prefixes that start with specific letters, particularly recognizing "wra" (as in "wrapped"), "jetty", "Loch", and "glomer" with high activation values.

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

The neuron fires strongly on subword pieces that begin longer or rarer words (i.e. the prefixes of multi-syllabic/low-frequency terms).

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

-2.84



-2.84

翾

-2.81

昞

-2.70

刧

-2.70

钐

-2.69

皤

-2.64

罍

-2.56

 tetapi

-2.50



-2.50

POSITIVE LOGITS

</strong>

3.22

</h3>

3.06

’

2.86

.“

2.55

 Eigentum

2.50

al

2.48

夲

2.36

2.34

 связанные

2.31

“

2.28

Activations Density 0.032%

glomerular disease

This neuron detects words or prefixes that start with specific letters, particularly recognizing "wra" (as in "wrapped"), "jetty", "Loch", and "glomer" with high activation values.

The neuron fires strongly on subword pieces that begin longer or rarer words (i.e. the prefixes of multi-syllabic/low-frequency terms).

No Comments

No Known Activations

glomerular disease

This neuron detects words or prefixes that start with specific letters, particularly recognizing "wra" (as in "wrapped"), "jetty", "Loch", and "glomer" with high activation values.

The neuron fires strongly on subword pieces that begin longer or rarer words (i.e. the prefixes of multi-syllabic/low-frequency terms).

No Comments

No Known Activations