© 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. 64368
    Prev
    Next
    INDEX
    Explanations

    public static, private static

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

    The neuron fires on access‐modifier keywords (like “public” or “private,” often paired with “static”) that mark class member and method declarations.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    TextEditing
    -1.09
    chnung
    -0.98
    幸いです
    -0.94
    ār
    -0.93
     distance
    -0.92
     timmar
    -0.91
     доступ
    -0.89
    ادم
    -0.89
    けどね
    -0.88
    itiés
    -0.88
    POSITIVE LOGITS
     wtedy
    1.04
     their
    1.01
     we
    1.00
    大丈夫です
    0.99
    おそ
    0.99
     uitgebre
    0.97
     kelebihan
    0.96
    cloudfront
    0.95
    romeda
    0.94
    γμα
    0.93
    Activations Density 0.002%

    No Known Activations