INDEX

Explanations

cells and tissues

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

patterns describing cell types and their biological properties in scientific texts.

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

The neuron fires on words that set up broad scientific contexts or enumerate ranges—e.g. tokens like “given,” “range,” “different,” “human,” and “tissues”—i.e. phrases that specify the scope or variety of biological entities.

oai_token-act-pair · o4-mini Triggered by @jyhe0408

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_34/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

 afge

-0.77

 vòng

-0.76

癌

-0.74

 макси

-0.73

 Leute

-0.72

li

-0.72

 Kräfte

-0.70

re

-0.70

 Ordnung

-0.69

祈り

-0.68

POSITIVE LOGITS

 tissues

2.70

 tissue

2.58

 Tissues

2.27

tissue

2.13

Tissue

2.06

 Tissue

1.91

tiss

1.73

 organs

1.43

 tissu

1.34

 Organs

1.30

Activations Density 0.372%

cells and tissues

patterns describing cell types and their biological properties in scientific texts.

The neuron fires on words that set up broad scientific contexts or enumerate ranges—e.g. tokens like “given,” “range,” “different,” “human,” and “tissues”—i.e. phrases that specify the scope or variety of biological entities.

No Comments

No Known Activations

cells and tissues

patterns describing cell types and their biological properties in scientific texts.

The neuron fires on words that set up broad scientific contexts or enumerate ranges—e.g. tokens like “given,” “range,” “different,” “human,” and “tissues”—i.e. phrases that specify the scope or variety of biological entities.

No Comments

No Known Activations