© 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. 91062
    Prev
    Next
    INDEX
    Explanations

    available to

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

    code and math symbols

    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
    DanhMucSP
    0.46
    fclose
    0.46
    NEW
    0.46
    ];//
    0.45
    utu
    0.45
    ,//
    0.45
    吨
    0.44
    🚿
    0.44
     nieuw
    0.42
    rifle
    0.42
    POSITIVE LOGITS
     italiano
    0.52
    p
    0.52
     Dor
    0.52
     Alan
    0.52
    ит
    0.50
     Nol
    0.50
     Giorgio
    0.50
    ก
    0.50
    ต
    0.50
     Bors
    0.49
    Activations Density 0.000%

    No Known Activations