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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82829
    Prev
    Next
    INDEX
    Explanations

    polygons and geometries

    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
    祛
    -0.86
    webElement
    -0.85
    Visión
    -0.85
    bital
    -0.83
    neder
    -0.82
    っていきます
    -0.81
    Quantidade
    -0.78
    grate
    -0.77
    alcoholic
    -0.77
     家族
    -0.77
    POSITIVE LOGITS
     polygon
    1.82
     polygons
    1.79
     geometry
    1.72
     geometries
    1.62
    geometry
    1.48
    shp
    1.41
    Feature
    1.39
     Feature
    1.32
     shape
    1.31
     Shape
    1.30
    Activations Density 0.132%

    No Known Activations