INDEX

Explanations

combining data structures

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

function calls that combine or join data structures, particularly concatenation and binding operations.

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

The neuron activates on words denoting data‐combining operations (e.g. concatenate, bind, hstack, flatten).

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

 Empfindung

-1.81

 angegebenen

-1.68

沺

-1.63

 denne

-1.59

fiées

-1.55

ྥ

-1.55

感じる

-1.49

 isolato

-1.48

锲

-1.48

 Bewußt

-1.45

POSITIVE LOGITS

of

2.00

the

1.92

 diversité

1.55

 into

1.47

</em>

1.41

our

1.35

 diverses

1.34

给大家

1.31

for

1.30

 hausse

1.30

Activations Density 0.007%

combining data structures

function calls that combine or join data structures, particularly concatenation and binding operations.

The neuron activates on words denoting data‐combining operations (e.g. concatenate, bind, hstack, flatten).

No Comments

No Known Activations

combining data structures

function calls that combine or join data structures, particularly concatenation and binding operations.

The neuron activates on words denoting data‐combining operations (e.g. concatenate, bind, hstack, flatten).

No Comments

No Known Activations