INDEX

Explanations

extracellular matrix (ECM)

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

The neuron detects instances of "ECM" (extracellular matrix) and "Alec" (a person's name) in text.

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

The neuron flags single tokens that are capitalized names or acronyms (e.g. “Alec” or “ECM”).

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

打量

-2.67

。

-2.66

῞

-2.61

下一篇

-2.55

.\\

-2.53

聍

-2.52



-2.52

﹑

-2.48

 شیپور

-2.42

柩

-2.34

POSITIVE LOGITS

to

3.16

3.09

2.91

2.81

en

2.77

↵

2.66

猻

2.59

and

2.56

!”

2.53

out

2.52

Activations Density 0.007%

extracellular matrix (ECM)

The neuron detects instances of "ECM" (extracellular matrix) and "Alec" (a person's name) in text.

The neuron flags single tokens that are capitalized names or acronyms (e.g. “Alec” or “ECM”).

No Comments

No Known Activations

extracellular matrix (ECM)

The neuron detects instances of "ECM" (extracellular matrix) and "Alec" (a person's name) in text.

The neuron flags single tokens that are capitalized names or acronyms (e.g. “Alec” or “ECM”).

No Comments

No Known Activations