INDEX

Explanations

laboratory or lab related context

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

scientific or technical references to "lab" or "laboratory" in various contexts.

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

The neuron fires on mentions of “lab” (in forms like “lab.”, “lab-scale,” “lab‐quality,” or “Laboratory”) in technical or reference contexts.

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

 dieß

-2.30

罽

-2.28

 จาก

-2.27

赑

-2.22

 什么

-2.17

 risiko

-2.17

噲

-2.14

 desapar

-2.13



-2.11

腚

-2.02

POSITIVE LOGITS

2.50

with

2.45

</b>

2.38

It

2.34

2.25

by

2.19

 Erkennt

2.17

2.14

2.13

2.11

Activations Density 0.019%

laboratory or lab related context

scientific or technical references to "lab" or "laboratory" in various contexts.

The neuron fires on mentions of “lab” (in forms like “lab.”, “lab-scale,” “lab‐quality,” or “Laboratory”) in technical or reference contexts.

No Comments

No Known Activations

laboratory or lab related context

scientific or technical references to "lab" or "laboratory" in various contexts.

The neuron fires on mentions of “lab” (in forms like “lab.”, “lab-scale,” “lab‐quality,” or “Laboratory”) in technical or reference contexts.

No Comments

No Known Activations