INDEX

Explanations

magnification, magnify, magnifier

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

terms related to magnification, such as "magnified," "magnifier," and "magnification."

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

The neuron detects variations of the word stem “magnif-,” i.e. terms referring to magnification or magnifying.

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

 Thus

-2.19

 Because

-2.17

 Therefore

-2.11

 However

-2.11

are

-2.09

</b>

-2.06

 Only

-2.02

 Since

-1.96

 Especially

-1.95

有力

-1.94

POSITIVE LOGITS

凄い

2.31

あっという

2.30

⩴

2.28

イケ

2.27

苤

2.20

Would

2.19

お互

2.16

 وت

2.09

楽しみです

2.08

Somebody

2.06

Activations Density 0.003%

magnification, magnify, magnifier

terms related to magnification, such as "magnified," "magnifier," and "magnification."

The neuron detects variations of the word stem “magnif-,” i.e. terms referring to magnification or magnifying.

No Comments

No Known Activations

magnification, magnify, magnifier

terms related to magnification, such as "magnified," "magnifier," and "magnification."

The neuron detects variations of the word stem “magnif-,” i.e. terms referring to magnification or magnifying.

No Comments

No Known Activations