© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 35509
    Prev
    Next
    INDEX
    Explanations

    black swan events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oito
    0.82
    ામ
    0.77
     ۸
    0.74
     ocho
    0.73
     stanowi
    0.71
     acht
    0.69
     кише
    0.67
     tinham
    0.66
    ول
    0.64
     striis
    0.64
    POSITIVE LOGITS
    0.88
    ning
    0.82
    .
    0.79
    en
    0.73
     I
    0.68
     internalized
    0.66
    ,
    0.65
    celi
    0.64
    er
    0.62
    phs
    0.58
    Activations Density 0.001%

    No Known Activations