INDEX

Explanations

chemotactic classifiers

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

words related to machine learning classifiers and classification processes.

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

This neuron activates on occurrences of “classifier” (and related “classification”) in code or documentation.

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

quelize

-2.61

</sup>

-2.33

，「

-2.27

-2.20

–

-2.17

-2.14

 города

-2.13

 epitome

-2.13

на

-2.06

POSITIVE LOGITS

癭

2.41

乸

2.31

狴

2.28

咴

2.28

鉏

2.23

歘

2.22

鷙

2.22

鎹

2.19

 Spisak

2.14

Activations Density 0.004%

chemotactic classifiers

words related to machine learning classifiers and classification processes.

This neuron activates on occurrences of “classifier” (and related “classification”) in code or documentation.

No Comments

No Known Activations

chemotactic classifiers

words related to machine learning classifiers and classification processes.

This neuron activates on occurrences of “classifier” (and related “classification”) in code or documentation.

No Comments

No Known Activations