© 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. 10-GEMMASCOPE-RES-131K
    7. 6684
    Prev
    Next
    INDEX
    Explanations

    GIS, spatial, layers, geoserver, ArcGIS

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     invitado
    -1.51
     notre
    -1.34
    付ける
    -1.33
    $-.
    -1.29
     mencionados
    -1.27
    hush
    -1.25
     extranjeros
    -1.23
    evolve
    -1.21
     fieles
    -1.21
     tratados
    -1.21
    POSITIVE LOGITS
    3
    1.66
     plastico
    1.56
     alcun
    1.38
     tecnico
    1.30
    id
    1.27
    +
    1.25
     umano
    1.23
     vini
    1.19
     fisico
    1.19
     culturale
    1.18
    Activations Density 0.155%

    No Known Activations