© 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. 3607
    Prev
    Next
    INDEX
    Explanations

    Razor view and UI elements

    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
     distritos
    -0.77
    ন্
    -0.77
     NSString
    -0.76
    บาง
    -0.72
     Procter
    -0.72
    earning
    -0.69
    etu
    -0.69
    lfloor
    -0.68
    EClass
    -0.68
     Scarlet
    -0.68
    POSITIVE LOGITS
     gelas
    0.71
    ベーター
    0.65
     khúc
    0.63
     nah
    0.63
    ôi
    0.63
     Utara
    0.63
    Ries
    0.62
    gliere
    0.62
     annealed
    0.62
     стек
    0.61
    Activations Density 0.042%

    No Known Activations