© 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. 205340
    Prev
    Next
    INDEX
    Explanations

    github urls

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

    go library imports

    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
     үш
    0.55
    masında
    0.54
     سادہ
    0.51
     бў
    0.50
     ప్రేక్షకు
    0.50
    푀
    0.50
    QTTR
    0.50
    ດ້ານ
    0.49
    GEBURTS
    0.49
     رفتار
    0.49
    POSITIVE LOGITS
    r
    0.61
     Brotherhood
    0.56
     companies
    0.54
     Churches
    0.52
     of
    0.52
    w
    0.51
    _
    0.51
    v
    0.50
     Hodgson
    0.50
     brothers
    0.50
    Activations Density 0.001%

    No Known Activations