© 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. 10431
    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
    ການ
    0.86
    <0x9E>
    0.83
    <0xA4>
    0.82
    ották
    0.81
    ñón
    0.81
    جل
    0.80
    药品
    0.80
    🅴
    0.80
    ⵔ
    0.78
    <0xB2>
    0.77
    POSITIVE LOGITS
     but
    0.93
    ten
    0.93
     nonetheless
    0.92
    to
    0.90
    উল্লেখ্য
    0.88
     without
    0.88
    Ты
    0.88
     sogenannte
    0.88
     Nonetheless
    0.87
     hinzu
    0.87
    Activations Density 0.001%

    No Known Activations