INDEX

Explanations

villous tissue

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

variations of the root "Vil" in names, locations, and biological terms like "villous".

oai_token-act-pair · claude-3-7-sonnet-20250219

Triggered by @neilrathi

The neuron detects occurrences of the character sequence “Vil” (e.g. as the start of names or words).

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

Negative Logits

踽

-2.50

神

-2.47

↵

-2.45



-2.44

呖

-2.44

 econômica

-2.39

韪

-2.34

selben

-2.34

 великолеп

-2.33

Ruju

-2.31

POSITIVE LOGITS

 This

3.52

It

2.84

 While

2.69

 Just

2.56

Our

2.53

be

2.52

2.48

 will

2.45

 Someone

2.42

 Only

2.39

Activations Density 0.005%

villous tissue

variations of the root "Vil" in names, locations, and biological terms like "villous".

The neuron detects occurrences of the character sequence “Vil” (e.g. as the start of names or words).

No Known Activations

villous tissue

variations of the root "Vil" in names, locations, and biological terms like "villous".

The neuron detects occurrences of the character sequence “Vil” (e.g. as the start of names or words).

No Known Activations