INDEX

Explanations

offspring

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

The neuron detects the word "offspring" in scientific contexts, particularly in papers about reproduction, genetics, and child development.

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

The neuron fires strongly on words denoting biological offspring or progeny (e.g., “offspring,” “progeny”).

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

}$

-3.39

</strong>

-2.64

のは

-2.41

籥

-2.31

釓

-2.31

cipy

-2.11

or

-2.11

tigte

-2.06

</u>

-2.05

AddHtmlAttribute

-1.99

POSITIVE LOGITS

2.45

 概要

2.41

erintah

2.31

翆

2.16

 レスト

2.11

pecabe

2.08

ኹ

2.06

⢌

2.05

对于

2.02

驁

2.02

Activations Density 0.003%

offspring

The neuron detects the word "offspring" in scientific contexts, particularly in papers about reproduction, genetics, and child development.

The neuron fires strongly on words denoting biological offspring or progeny (e.g., “offspring,” “progeny”).

No Comments

No Known Activations

offspring

The neuron detects the word "offspring" in scientific contexts, particularly in papers about reproduction, genetics, and child development.

The neuron fires strongly on words denoting biological offspring or progeny (e.g., “offspring,” “progeny”).

No Comments

No Known Activations