© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25215
    Prev
    Next
    INDEX
    Explanations

    property string, psychoanalytic

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

    The neuron reliably fires on PHPDoc “@property” annotation lines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     kabát
    -1.81
     biela
    -1.66
     bahagia
    -1.59
     dimas
    -1.56
     pás
    -1.55
    ꉂ
    -1.54
     kapit
    -1.50
     mikina
    -1.50
     blusa
    -1.48
     abiye
    -1.47
    POSITIVE LOGITS
    ,
    2.03
    1.90
     is
    1.71
    is
    1.69
    -
    1.68
    o
    1.63
    <i>
    1.63
    b
    1.62
    s
    1.59
    1.59
    Activations Density 0.000%
    No Known Activations