INDEX

Explanations

protease and related enzymes

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

This neuron identifies proteins and enzymes related to proteases and proteolytic activity in scientific/biochemical contexts.

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

The neuron selectively activates on enzyme names—especially proteases—by picking up the “-ase” suffix (and related stems like “prote-” in words like “protease”).

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

禩

-1.99

⦊

-1.80

 According

-1.77

猹

-1.64

based

-1.61

櫺

-1.60

when

-1.59

istani

-1.58

 Accordingly

-1.56

fying

-1.55

POSITIVE LOGITS

2.36

↵

2.05

1.80

沨

1.52

 tussen

1.48

 zonder

1.46

ྵ

1.42

٤

1.41

ont

1.41

ྜ

1.41

Activations Density 0.134%

protease and related enzymes

This neuron identifies proteins and enzymes related to proteases and proteolytic activity in scientific/biochemical contexts.

The neuron selectively activates on enzyme names—especially proteases—by picking up the “-ase” suffix (and related stems like “prote-” in words like “protease”).

No Comments

No Known Activations

protease and related enzymes

This neuron identifies proteins and enzymes related to proteases and proteolytic activity in scientific/biochemical contexts.

The neuron selectively activates on enzyme names—especially proteases—by picking up the “-ase” suffix (and related stems like “prote-” in words like “protease”).

No Comments

No Known Activations