© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79307
    Prev
    Next
    INDEX
    Explanations

    Kabru; Chinese; list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     at
    -0.96
    ราคา
    -0.94
    lanması
    -0.93
    DrawerToggle
    -0.91
     áreas
    -0.91
    urazione
    -0.90
     rique
    -0.88
    Ừ
    -0.88
    URLConnection
    -0.87
    рию
    -0.87
    POSITIVE LOGITS
     list
    1.82
     List
    1.77
    List
    1.71
    list
    1.54
     lista
    1.13
     قائمة
    1.05
     liste
    1.04
     LIST
    0.99
     список
    0.96
     ventes
    0.96
    Activations Density 0.003%

    No Known Activations