© 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. 10044
    Prev
    Next
    INDEX
    Explanations

    void methods, override

    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
    да
    1.14
     mellitus
    1.07
     PERCENT
    0.96
     follicle
    0.95
    ле
    0.92
    ダイエット
    0.92
    ла
    0.91
    蜒
    0.91
     sweetener
    0.91
     comedic
    0.86
    POSITIVE LOGITS
     ただ
    1.05
    ?”,
    1.05
    ys
    1.02
     antes
    1.00
     sido
    0.97
    内に
    0.96
    yards
    0.93
     obtenido
    0.93
    in
    0.93
    steps
    0.92
    Activations Density 0.062%

    No Known Activations