© 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. 87321
    Prev
    Next
    INDEX
    Explanations

    desiderio

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

    discovering value

    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
    Star
    0.51
    コイル
    0.50
    閾
    0.50
    embalikan
    0.49
    ill
    0.48
    ાર
    0.47
    star
    0.47
    omus
    0.46
    onik
    0.46
    har
    0.46
    POSITIVE LOGITS
     知
    0.63
     riz
    0.48
     tiver
    0.48
     desi
    0.47
     Know
    0.46
     ligado
    0.46
     jist
    0.46
     manda
    0.45
     desider
    0.45
     ris
    0.45
    Activations Density 0.001%

    No Known Activations