© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104482
    Prev
    Next
    INDEX
    Explanations

    c++ structure fields

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

    variable names and identifiers in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron specifically lights up on numeric tokens (digits or numbers) in code, such as integer literals, numeric type or array‐size specifiers, and identifiers containing digits.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     it
    -1.76
     with
    -1.67
     in
    -1.52
     nuestros
    -1.52
    %");
    -1.45
    ₇
    -1.39
    																						
    -1.38
     în
    -1.37
     on
    -1.35
    																										
    -1.34
    POSITIVE LOGITS
    Приложение
    1.55
    这才
    1.38
    \
    1.30
    Иван
    1.28
    Михаил
    1.23
    葡萄酒
    1.21
    できるので
    1.20
    かったので
    1.20
    DÉ
    1.19
    Опыт
    1.18
    Activations Density 0.009%

    No Known Activations