© 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. 235231
    Prev
    Next
    INDEX
    Explanations

    target setthey sharedwill helpfacilitates Internet

    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
    oliberal
    0.52
    il
    0.49
    fy
    0.47
    kinetic
    0.46
    F
    0.46
    vercel
    0.46
    weave
    0.46
    N
    0.45
    o
    0.45
     ड्यू
    0.45
    POSITIVE LOGITS
     étape
    0.50
     bunches
    0.47
     இருப்பினும்
    0.45
     extrémité
    0.45
    지만
    0.44
     مقاوم
    0.44
     جر
    0.42
     不需要
    0.42
     damaged
    0.42
     ér
    0.42
    Activations Density 0.000%

    No Known Activations