© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 52147
    Prev
    Next
    INDEX
    Explanations

    data types and formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_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
     to
    0.51
    _
    0.49
    You
    0.48
     indist
    0.46
    mck
    0.45
     you
    0.45
    ITZ
    0.45
     모든
    0.43
    ⅔
    0.43
    Anyone
    0.43
    POSITIVE LOGITS
     Благодаря
    0.46
     වශ
    0.44
     Lebih
    0.44
     bezig
    0.42
     बदलने
    0.40
    రించే
    0.40
     Também
    0.40
    Descrição
    0.40
     phú
    0.40
     Nhưng
    0.40
    Activations Density 0.000%

    No Known Activations