© 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. 180063
    Prev
    Next
    INDEX
    Explanations

    cannot guarantee

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

    local access and limitations

    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
    ua
    0.56
     policewomen
    0.50
     waterproofing
    0.50
     accessory
    0.47
    rification
    0.45
    iferous
    0.44
    otyping
    0.44
     withd
    0.44
    ’
    0.44
    uate
    0.44
    POSITIVE LOGITS
    玑
    0.53
     creciente
    0.49
     مای
    0.49
     يم
    0.48
     costruito
    0.47
    Jahr
    0.47
    Integrante
    0.47
     координаты
    0.46
    ।]
    0.46
    BEN
    0.46
    Activations Density 0.003%

    No Known Activations