© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 246547
    Prev
    Next
    INDEX
    Explanations

    texts with various accents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵↵↵↵↵
    0.51
    ={
    0.51
    OUS
    0.50
    ":[
    0.48
    ಪ್ಪು
    0.47
    ↵↵
    0.46
    ↵↵↵↵
    0.46
    ">
    0.46
    ల్య
    0.46
    加载
    0.46
    POSITIVE LOGITS
     dinámica
    0.54
     piattaforma
    0.49
     publicação
    0.48
     récemment
    0.48
     algunas
    0.47
     наших
    0.47
     pediu
    0.47
     некоторых
    0.47
     några
    0.47
     manifestó
    0.46
    Activations Density 0.001%

    No Known Activations