© 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. 56838
    Prev
    Next
    INDEX
    Explanations

    local institutions

    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
     quantités
    -0.92
     ketidak
    -0.90
    ندن
    -0.90
    】:
    -0.89
    inerary
    -0.89
     aplicativos
    -0.89
    Ferdin
    -0.89
    Vicente
    -0.88
    开玩笑
    -0.88
     時尚
    -0.88
    POSITIVE LOGITS
     university
    2.22
     Chamber
    2.06
     library
    2.00
     hospital
    1.84
     police
    1.76
     universities
    1.69
     airport
    1.68
     chamber
    1.67
     church
    1.62
     college
    1.60
    Activations Density 0.074%

    No Known Activations