© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 111115
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and measurements

    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
     centerline
    -1.11
     center
    -1.01
     centre
    -0.95
    center
    -0.92
    센터
    -0.89
     centers
    -0.86
     центре
    -0.84
     CENTER
    -0.84
    Center
    -0.84
     Center
    -0.82
    POSITIVE LOGITS
     circle
    1.21
     region
    1.17
    circle
    1.04
     regions
    0.96
     ellipse
    0.90
    Region
    0.89
     región
    0.88
     triangle
    0.86
    Circle
    0.86
     wilayah
    0.84
    Activations Density 0.073%

    No Known Activations