© 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. 34876
    Prev
    Next
    INDEX
    Explanations

    cardio exercise

    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
    س
    1.03
    1
    0.93
    .
    0.81
    ح
    0.78
    '
    0.71
    itchie
    0.69
     esprit
    0.69
    壹
    0.66
    स
    0.63
    ait
    0.62
    POSITIVE LOGITS
    u
    1.22
    er
    0.89
    in
    0.82
    ו
    0.79
    و
    0.79
    ার
    0.74
    すぐに
    0.74
    یان
    0.73
     Kullan
    0.71
    噰
    0.68
    Activations Density 0.001%

    No Known Activations