INDEX

Explanations

syndrome variants

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

medical and scientific terminology with prefixes like "sy" and "syndrome".

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

The neuron is strongly activated by the character sequence “sy” at the start of subwords (e.g. Syro-, syndrome, synapses, synovial, etc.).

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

New Auto-Interp

Configuration

google/gemma-scope-27b-pt-res/layer_22/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

↵

-2.73

</strong>

-2.50

-2.33

瑨

-2.27

-2.17

it

-2.16

 inviting

-2.05

気軽

-2.05

 segurando

-2.03

慙

-2.02

POSITIVE LOGITS

}}

2.72

2.52

In

2.45

On

2.38

蹙

2.28

2.25

디오

2.23

ol

2.20

Activations Density 0.036%

syndrome variants

medical and scientific terminology with prefixes like "sy" and "syndrome".

The neuron is strongly activated by the character sequence “sy” at the start of subwords (e.g. Syro-, syndrome, synapses, synovial, etc.).

No Comments

No Known Activations

syndrome variants

medical and scientific terminology with prefixes like "sy" and "syndrome".

The neuron is strongly activated by the character sequence “sy” at the start of subwords (e.g. Syro-, syndrome, synapses, synovial, etc.).

No Comments

No Known Activations