© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8479
    Prev
    Next
    INDEX
    Explanations

    code line comments

    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_31_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
     piece
    0.56
     inmedi
    0.55
     need
    0.54
     word
    0.54
     pieces
    0.52
     Piece
    0.52
    KEA
    0.50
    ซ
    0.50
     medias
    0.49
     \
    0.49
    POSITIVE LOGITS
     மிரு
    0.59
    Entre
    0.58
    cJ
    0.58
    ێت
    0.57
     aDecoder
    0.54
    udah
    0.54
     можна
    0.52
    বাহী
    0.52
    InputBorder
    0.52
    ltre
    0.52
    Activations Density 0.000%

    No Known Activations