© 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. 10485
    Prev
    Next
    INDEX
    Explanations

    List prefixes

    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
    tól
    0.80
    t
    0.77
    smanship
    0.75
    gomery
    0.71
    te
    0.70
    يات
    0.70
    tım
    0.67
    тів
    0.66
    tı
    0.65
    ில்
    0.65
    POSITIVE LOGITS
     և
    0.81
    ्य
    0.74
    ар
    0.71
    もっと
    0.71
    8
    0.70
     emeritus
    0.69
    但
    0.69
     а
    0.68
    る
    0.68
    6
    0.67
    Activations Density 0.000%

    No Known Activations