© 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. 41856
    Prev
    Next
    INDEX
    Explanations

    Reykjavik, networks, Endpoints, book, articles, bach

    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
    近平
    1.41
    <0xA6>
    1.38
     তার
    1.38
    通过
    1.34
    お店
    1.34
    有
    1.30
    साठी
    1.29
    运算符
    1.29
    不需要
    1.25
    人民政府
    1.25
    POSITIVE LOGITS
    et
    1.48
    as
    1.47
    ла
    1.47
    т
    1.42
    it
    1.41
    ent
    1.41
    j
    1.38
    agles
    1.32
    filtration
    1.31
    и
    1.28
    Activations Density 0.000%

    No Known Activations