INDEX

Explanations

storage, memory, GB

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

mentions of digital storage capacity (gigabytes) and data storage contexts.

oai_token-act-pair · claude-4-5-sonnet Triggered by @bfgcn7frf5

The neuron fires on numeric measurements and quantities (especially data/storage sizes and other numbers).

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

</sup>

-1.46

"""

-1.34

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.32

 todavía

-1.28

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.28

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.27

 lorsqu

-1.26

still

-1.25

↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵

-1.22

</em>

-1.22

POSITIVE LOGITS

でもいい

1.23

 adding

1.23

 choosing

1.16

Или

1.15

 dazzling

1.12

 selecting

1.07

的吗

1.06

Сю

1.05

Alemania

1.04

的情况

1.03

Activations Density 0.091%

storage, memory, GB

mentions of digital storage capacity (gigabytes) and data storage contexts.

The neuron fires on numeric measurements and quantities (especially data/storage sizes and other numbers).

No Comments

No Known Activations

storage, memory, GB

mentions of digital storage capacity (gigabytes) and data storage contexts.

The neuron fires on numeric measurements and quantities (especially data/storage sizes and other numbers).

No Comments

No Known Activations