© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 124690
    Prev
    Next
    INDEX
    Explanations

    typedef struct

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

    The neuron strongly activates on C/C++ unsigned integer type specifiers (e.g. "unsigned", "short", "long", "uint16", etc.) in typedef or struct declarations.

    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
    蚰
    -1.92
     货
    -1.75
     INCOR
    -1.68
     DETAIL
    -1.68
     uly
    -1.66
    猻
    -1.66
    嘥
    -1.64
    ympto
    -1.63
     THEOREM
    -1.63
    很快
    -1.62
    POSITIVE LOGITS
     more
    2.52
     an
    2.16
     in
    2.09
     There
    2.06
     all
    2.03
     From
    1.90
     well
    1.87
    ,
    1.86
     In
    1.84
     first
    1.83
    Activations Density 0.007%

    No Known Activations