INDEX

Explanations

species

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

The neuron activates for the scientific term "species" when used in technical or taxonomic contexts, particularly when discussing biological classification or chemical compounds.

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

This neuron activates on numeric tokens (numbers or numeric sequences) in the text.

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

༷

-2.55

’.”

-2.22

")){

-2.19

泚

-2.19

.」

-2.16

.).

-2.14

捩

-2.13

های

-2.09

 liée

-2.08

ScopeManager

-2.03

POSITIVE LOGITS

Donde

2.53

ஂ

2.23

篌

2.14

شكرا

2.09

Cocina

2.05

2.03

 possess

2.00

Conclusión

2.00

ญี่ป

1.98

鲠

1.96

Activations Density 0.021%

species

The neuron activates for the scientific term "species" when used in technical or taxonomic contexts, particularly when discussing biological classification or chemical compounds.

This neuron activates on numeric tokens (numbers or numeric sequences) in the text.

No Comments

No Known Activations

species

The neuron activates for the scientific term "species" when used in technical or taxonomic contexts, particularly when discussing biological classification or chemical compounds.

This neuron activates on numeric tokens (numbers or numeric sequences) in the text.

No Comments

No Known Activations