© 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. 229473
    Prev
    Next
    INDEX
    Explanations

    things from it every

    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
    我们要
    0.48
     распространен
    0.46
    🔳
    0.46
    来源
    0.45
    全球
    0.44
     різ
    0.44
    StringType
    0.44
    年末
    0.43
    ف
    0.43
    ዩ
    0.43
    POSITIVE LOGITS
    energ
    0.54
     परेशानियों
    0.53
    imenta
    0.49
     મહે
    0.48
    zyn
    0.48
     내
    0.47
     Mandal
    0.47
     energ
    0.47
     Ring
    0.46
     dong
    0.46
    Activations Density 0.000%

    No Known Activations