© 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. 65892
    Prev
    Next
    INDEX
    Explanations

    foreign languages

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

    questions about configuration and time

    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
    CE
    0.55
    {"
    0.51
    MON
    0.51
     t
    0.48
    ++
    0.46
    REC
    0.46
    PRO
    0.45
     {
    0.45
    2
    0.45
    _
    0.45
    POSITIVE LOGITS
    configured
    0.53
     თავ
    0.52
     скон
    0.52
     delanter
    0.52
     доступа
    0.52
    namento
    0.52
    䐈
    0.51
     अजय
    0.50
     выполнен
    0.50
     सहित
    0.50
    Activations Density 0.000%

    No Known Activations