© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 38716
    Prev
    Next
    INDEX
    Explanations

    being observed and used

    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
    am
    0.87
    in
    0.76
    c
    0.76
    o
    0.69
    ad
    0.68
    cl
    0.68
     corresponding
    0.66
    öre
    0.66
    D
    0.66
    W
    0.65
    POSITIVE LOGITS
     dehuman
    0.92
     වීම
    0.89
    يان
    0.85
     unfit
    0.82
     engender
    0.82
    মেন্ট
    0.81
     Kyng
    0.80
    ِمض
    0.79
     Hairst
    0.79
    癤
    0.79
    Activations Density 0.000%

    No Known Activations