© 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-16K
    7. 12184
    Prev
    Next
    INDEX
    Explanations

    status of

    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_16k_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
    ad
    2.77
    and
    2.30
    说
    2.25
    am
    2.14
    or
    2.02
    ד
    2.02
    ur
    2.00
    le
    1.96
    the
    1.88
    ap
    1.86
    POSITIVE LOGITS
    ны
    2.03
    ных
    1.99
     especializados
    1.90
    ्लाई
    1.78
    ו
    1.73
    вы
    1.73
    ش
    1.73
    ست
    1.71
    uario
    1.71
    ت
    1.69
    Activations Density 0.021%

    No Known Activations