© 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. 88466
    Prev
    Next
    INDEX
    Explanations

    significantly less, distinguish themselves, gather evidence

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

    software and verification

    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
     Trouver
    0.46
     Índice
    0.45
    CA
    0.44
     Ş
    0.44
     Livingstone
    0.44
    MUN
    0.42
    UT
    0.42
     Σ
    0.42
    kan
    0.41
     Τ
    0.41
    POSITIVE LOGITS
    hattim
    0.48
     практика
    0.45
     অনেকটাই
    0.45
    routingHeader
    0.44
     warships
    0.43
     assets
    0.43
    ן
    0.42
     обеща
    0.42
     ресур
    0.42
     मायने
    0.42
    Activations Density 0.001%

    No Known Activations