© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58418
    Prev
    Next
    INDEX
    Explanations

    surrounding areas and suburbs

    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
     prioridades
    -1.30
     temáticas
    -1.08
     another
    -1.05
     asociaciones
    -1.00
    itens
    -0.98
     each
    -0.98
     possibilities
    -0.97
     readily
    -0.97
     sentimiento
    -0.96
     fearing
    -0.96
    POSITIVE LOGITS
     surrounding
    1.70
    areas
    1.62
     areas
    1.52
     Areas
    1.36
    Areas
    1.30
    area
    1.30
     area
    1.27
    greater
    1.27
    AREA
    1.27
    Clients
    1.22
    Activations Density 0.056%

    No Known Activations