INDEX

Explanations

code structures and symbols

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

opening braces of function definitions in code.

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

This neuron detects the “() {” (or “=> {”) pattern that begins JavaScript function bodies.

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

of

-3.19

to

-2.83

it

-2.75

-2.48

he

-2.47

for

-2.39

lot

-2.30

was

-2.25

we

-2.22

and

-2.19

POSITIVE LOGITS

 humeur

2.61

 patienter

2.48

猻

2.41

沵

2.36

饜

2.34

 patate

2.31

itespace

2.25

ᓚ

2.23

 插画

2.22

وكان

2.22

Activations Density 0.001%

code structures and symbols

opening braces of function definitions in code.

This neuron detects the “() {” (or “=> {”) pattern that begins JavaScript function bodies.

No Comments

No Known Activations

code structures and symbols

opening braces of function definitions in code.

This neuron detects the “() {” (or “=> {”) pattern that begins JavaScript function bodies.

No Comments

No Known Activations