© 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. 63264
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    versatile communication requirements

    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
     forskj
    0.46
    vien
    0.43
    ConformanceMode
    0.43
    sah
    0.41
    shy
    0.41
    ym
    0.41
    én
    0.41
    痱
    0.41
    askan
    0.40
     শান্তির
    0.40
    POSITIVE LOGITS
    %]
    0.55
    🅷
    0.49
     позволи
    0.49
    ıldığı
    0.47
    ],”
    0.47
    nD
    0.47
     від
    0.46
     thửa
    0.46
     порядка
    0.46
     pengg
    0.46
    Activations Density 0.000%

    No Known Activations