© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 46431
    Prev
    Next
    INDEX
    Explanations

    locations and points in space

    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
    this
    0.92
    с
    0.81
    as
    0.79
    do
    0.79
    these
    0.78
    ар
    0.73
     tohoto
    0.73
    of
    0.72
    ต์
    0.71
    umuz
    0.70
    POSITIVE LOGITS
    abouts
    0.89
    h
    0.82
     is
    0.78
    在
    0.72
     ওখানে
    0.71
    ifrån
    0.68
    ও
    0.67
    aj
    0.62
     moistur
    0.61
    在那里
    0.57
    Activations Density 0.017%

    No Known Activations