INDEX

Explanations

lentils, virus, pulses, lentiviral

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

scientific or technical terms, particularly those related to biological organisms, viruses, and optical components.

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

The neuron is triggered by any token containing the character sequence “lenti” (as in lentils, lenti–).

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

 stück

-2.41

 hohem

-2.38

瑒

-2.31

懌

-2.23

 gelieb

-2.20

đầm

-2.19

ᐕ

-2.17

 vorgesehen

-2.16

贏

-2.11

 vielen

-2.06

POSITIVE LOGITS

3.13

("

2.36

ſelf

2.30

 modifica

2.23

2.08

…"

2.06

borderSide

2.03

 will

2.00

屃

1.98

в

1.97

Activations Density 0.008%

lentils, virus, pulses, lentiviral

scientific or technical terms, particularly those related to biological organisms, viruses, and optical components.

The neuron is triggered by any token containing the character sequence “lenti” (as in lentils, lenti–).

No Comments

No Known Activations

lentils, virus, pulses, lentiviral

scientific or technical terms, particularly those related to biological organisms, viruses, and optical components.

The neuron is triggered by any token containing the character sequence “lenti” (as in lentils, lenti–).

No Comments

No Known Activations