INDEX

Explanations

replication, reputation, repacked, repressor, repels

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

The neuron detects the word "rep" and related terms like "replication" and "replicate" in technical computing or database contexts.

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

The neuron fires on any occurrence of the letter sequence “rep” (as in replication, replicate, repacking, reputation, etc.).

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

↵↵

-2.98

-2.59

."

-2.58

-2.50

-2.48

 refine

-2.41

-2.39

 leeren

-2.34

 resurrect

-2.33

-2.30

POSITIVE LOGITS

佧

3.33

Ꮵ

2.86

⢌

2.84

涐

2.75

 Mahasiswa

2.73

 utilizzato

2.73

 inconvénients

2.70

 anser

2.66

 torner

2.64

ﱠ

2.61

Activations Density 0.015%

replication, reputation, repacked, repressor, repels

The neuron detects the word "rep" and related terms like "replication" and "replicate" in technical computing or database contexts.

The neuron fires on any occurrence of the letter sequence “rep” (as in replication, replicate, repacking, reputation, etc.).

No Comments

No Known Activations

replication, reputation, repacked, repressor, repels

The neuron detects the word "rep" and related terms like "replication" and "replicate" in technical computing or database contexts.

The neuron fires on any occurrence of the letter sequence “rep” (as in replication, replicate, repacking, reputation, etc.).

No Comments

No Known Activations