© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 191347
    Prev
    Next
    INDEX
    Explanations

    particles, defense, want, challenge, company, must, bar, calf

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

    speaking about opening conversations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     racially
    0.57
    '
    0.57
    removeClass
    0.48
     राजस्व
    0.47
    finaly
    0.47
    false
    0.47
     false
    0.47
     '
    0.46
    GetCurrent
    0.46
    ते
    0.46
    POSITIVE LOGITS
    ந்தை
    0.52
     underside
    0.48
    ಾಗುತ್ತದೆ
    0.46
    تھی
    0.46
     بالا
    0.46
    လိုအပ်
    0.46
    ARKS
    0.45
     കാര
    0.45
     Maa
    0.45
     składa
    0.45
    Activations Density 0.001%

    No Known Activations