© 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. 207304
    Prev
    Next
    INDEX
    Explanations

    athletes, license, code, name

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

    download necessary resources

    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
    斑
    0.49
    PubMed
    0.48
     Харків
    0.48
    溶液
    0.48
    炎
    0.48
     КП
    0.47
     በሽታ
    0.47
    後
    0.47
     поми
    0.47
     теории
    0.46
    POSITIVE LOGITS
     denote
    0.49
    .
    0.48
    لاح
    0.46
    고자
    0.46
     asiento
    0.44
     dishonest
    0.43
    stice
    0.43
     electoral
    0.43
    incy
    0.43
    ifs
    0.42
    Activations Density 0.000%

    No Known Activations