© 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. 169008
    Prev
    Next
    INDEX
    Explanations

    operating systems android windows

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

    Windows and Linux operating systems

    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
    եր
    0.59
    عا
    0.57
    leştir
    0.52
     inad
    0.52
    旪
    0.52
    ığ
    0.50
     in
    0.49
    t
    0.49
     ότι
    0.48
    "];
    0.48
    POSITIVE LOGITS
    珞
    0.56
     thaliana
    0.55
    os
    0.50
    VAL
    0.50
    駭
    0.50
     rye
    0.49
    雑貨
    0.49
    スタート
    0.49
    ans
    0.48
    ного
    0.48
    Activations Density 0.057%

    No Known Activations