© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 34776
    Prev
    Next
    INDEX
    Explanations

    hardware, if, any, here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     errores
    0.75
     Bạch
    0.75
    льных
    0.75
     Youtube
    0.75
     sluč
    0.74
    keiten
    0.73
    `],
    0.72
    ష్య
    0.72
    лены
    0.72
    kach
    0.72
    POSITIVE LOGITS
    ف
    1.29
    ي
    1.02
    ب
    0.89
    ی
    0.88
     conseiller
    0.87
    احت
    0.87
    т
    0.86
    و
    0.86
    他
    0.84
     meilleur
    0.83
    Activations Density 0.000%

    No Known Activations