© 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. 71461
    Prev
    Next
    INDEX
    Explanations

    documentation blocks

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

    The neuron detects documentation‐style comment markers (e.g. /*!, //!, @header, @brief) in source code.

    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
     菇
    -2.02
    暃
    -1.82
    魠
    -1.79
    䛗
    -1.69
    帶來
    -1.62
    傒
    -1.59
    縢
    -1.58
    賸
    -1.57
    羕
    -1.55
     być
    -1.53
    POSITIVE LOGITS
     should
    1.77
     can
    1.74
     for
    1.73
     doesn
    1.67
     could
    1.59
     will
    1.54
     does
    1.54
     has
    1.54
     '
    1.48
     seems
    1.48
    Activations Density 0.042%

    No Known Activations