© 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. 14682
    Prev
    Next
    INDEX
    Explanations

    specifying data format structures

    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
     in
    1.21
    ,
    0.88
     by
    0.79
    ید
    0.74
    在
    0.73
     control
    0.68
     panel
    0.66
     b
    0.66
     morale
    0.66
    t
    0.66
    POSITIVE LOGITS
    Formatting
    0.87
    ０
    0.81
    格式
    0.80
    Format
    0.79
     formatos
    0.79
     fórmulas
    0.77
     Formatting
    0.74
    Formatter
    0.73
     Cómo
    0.73
    formats
    0.73
    Activations Density 0.045%

    No Known Activations