© 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. 176419
    Prev
    Next
    INDEX
    Explanations

    potential, biomedical, return

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

    . cx="50" and cy="50"

    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
    Negative Logits
     you
    0.53
    ira
    0.48
    ambar
    0.46
    acı
    0.46
     retrieving
    0.46
    iyar
    0.45
    ovala
    0.45
    x
    0.45
    H
    0.44
    ες
    0.44
    POSITIVE LOGITS
    堅持
    0.50
    льти
    0.46
    servic
    0.45
     proté
    0.45
    サービス
    0.45
    bete
    0.45
     représ
    0.45
     ejes
    0.45
    ენ
    0.44
    melee
    0.44
    Activations Density 0.000%

    No Known Activations