© 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. 41196
    Prev
    Next
    INDEX
    Explanations

    project successes

    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
    té
    0.94
    től
    0.94
    ﺫ
    0.93
    tól
    0.91
    ^{*}}
    0.88
    แต่ละ
    0.86
    టా
    0.84
    分析
    0.83
    tia
    0.82
    வேறு
    0.82
    POSITIVE LOGITS
    an
    0.86
    ivism
    0.84
    о
    0.84
    re
    0.81
    kiem
    0.81
    adamu
    0.80
    oleum
    0.79
     Miles
    0.78
    ной
    0.77
    otypes
    0.77
    Activations Density 0.000%

    No Known Activations