© 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. 117851
    Prev
    Next
    INDEX
    Explanations

    new in german, spanish, french, or russian

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

    UBI, Safety Record, SSO configurations, brand loyalty

    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
    kho
    0.46
    ूप
    0.44
    וו
    0.44
    russ
    0.44
    Ꮋ
    0.44
    WH
    0.43
     temperatur
    0.43
     krvi
    0.43
     koszt
    0.42
    🤍
    0.42
    POSITIVE LOGITS
     Neuen
    0.50
     Nueva
    0.48
     Taschen
    0.48
     Nouvelle
    0.47
     Otro
    0.45
     Nova
    0.45
    нова
    0.43
     Geist
    0.43
     Colonia
    0.43
     Dov
    0.43
    Activations Density 0.002%

    No Known Activations