© 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. 47099
    Prev
    Next
    INDEX
    Explanations

    National + specific entities/places

    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
    HIB
    -0.74
     microfibra
    -0.73
    历史
    -0.72
    GroupLayout
    -0.71
     TÉCNICA
    -0.71
    舒适
    -0.70
     peculi
    -0.70
    xmax
    -0.69
     domesti
    -0.69
     gili
    -0.69
    POSITIVE LOGITS
     highways
    0.83
     Sample
    0.81
     Illness
    0.79
     Highways
    0.77
     energii
    0.74
    imų
    0.74
    🏙
    0.73
    ized
    0.72
     meget
    0.70
     waterways
    0.70
    Activations Density 0.017%

    No Known Activations