© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 44781
    Prev
    Next
    INDEX
    Explanations

    json and html 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
    Negative Logits
    ում
    0.51
    스를
    0.51
    ˒
    0.51
    스와
    0.49
    되며
    0.49
    एं
    0.46
    ༠
    0.46
     словами
    0.46
    ც
    0.45
     earners
    0.45
    POSITIVE LOGITS
    na
    0.60
    <blockquote>
    0.54
     TMZ
    0.52
     Problem
    0.52
    <h2>
    0.49
    <h1>
    0.49
    k
    0.49
    not
    0.48
    <h3>
    0.48
     nedostat
    0.48
    Activations Density 0.011%

    No Known Activations