© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34246
    Prev
    Next
    INDEX
    Explanations

    ultimate goals

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

    charts, specific datasets, LiDAR, Camry, Ultimate Guide

    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
    MADE
    0.46
     सामील
    0.44
     busque
    0.44
    ़
    0.44
    าย
    0.43
     स्कूली
    0.43
     busca
    0.42
     QUE
    0.42
    ubjects
    0.42
     यर
    0.42
    POSITIVE LOGITS
     Prud
    0.49
     Allerdings
    0.45
    objectManager
    0.44
     antipode
    0.40
    </th>
    0.40
    Corporate
    0.39
     Carpent
    0.39
    ムー
    0.38
    sschutz
    0.38
     CCP
    0.37
    Activations Density 0.000%

    No Known Activations