© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 36009
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Более
    0.95
     تطبيق
    0.94
     Бы
    0.88
     Такие
    0.88
     государственных
    0.87
    Ｖ
    0.87
     товары
    0.87
     Боль
    0.86
     ت
    0.84
     т
    0.82
    POSITIVE LOGITS
     earring
    0.87
    ţi
    0.74
     fist
    0.73
    نا
    0.72
     endroits
    0.72
     nails
    0.71
     electrolysis
    0.71
     leaves
    0.70
     neighbors
    0.70
    фона
    0.70
    Activations Density 0.000%

    No Known Activations