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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71882
    Prev
    Next
    INDEX
    Explanations

    C++ move semantics and syntax

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

    The neuron primarily fires on occurrences of the token “move” in code (e.g. std::move, move constructors, function names).

    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
     tomba
    -2.09
    饜
    -1.85
     SolutionA
    -1.79
     Infór
    -1.78
     SUPREME
    -1.73
    肏
    -1.73
    珢
    -1.69
    艄
    -1.67
    聞いた
    -1.67
    ?」
    -1.66
    POSITIVE LOGITS
    ;
    2.14
    —
    1.88
    These
    1.87
    ’
    1.82
    They
    1.73
    ",
    1.59
    This
    1.58
     ,
    1.54
     [
    1.54
    ),
    1.52
    Activations Density 0.002%

    No Known Activations