© 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. 78035
    Prev
    Next
    INDEX
    Explanations

    pieces and

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

    action followed by detail

    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
    стре
    0.46
     bija
    0.44
     calyce
    0.43
     toneladas
    0.43
    噸
    0.43
     sedikit
    0.43
     coniferous
    0.43
    πλ
    0.42
     scopo
    0.42
     implementing
    0.42
    POSITIVE LOGITS
     મા
    0.46
    ⼯
    0.44
     فرو
    0.44
    Atual
    0.44
    ድን
    0.44
    fromi
    0.43
    Dragged
    0.43
    फेक्शन
    0.42
     माफी
    0.42
    MaxSize
    0.42
    Activations Density 0.001%

    No Known Activations