© 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. 106482
    Prev
    Next
    INDEX
    Explanations

    place names and locations

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Orkney
    -0.99
    醍
    -0.97
    кухня
    -0.95
    RRP
    -0.90
     fatis
    -0.90
     ребё
    -0.88
     الشاشة
    -0.88
     Garda
    -0.87
     proteine
    -0.87
    動機
    -0.87
    POSITIVE LOGITS
    ḻ
    1.05
    tham
    1.05
    ſh
    0.97
     doby
    0.94
    croft
    0.94
     astore
    0.93
    ington
    0.93
    نجليز
    0.93
    で見る
    0.93
     Anlagen
    0.92
    Activations Density 0.091%

    No Known Activations