© 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. 53827
    Prev
    Next
    INDEX
    Explanations

    geometric points and intersections

    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
    plano
    -0.90
    ずつ
    -0.82
     política
    -0.82
    Política
    -0.79
     demografica
    -0.77
    磬
    -0.77
    terrasse
    -0.77
    kalender
    -0.77
    alık
    -0.76
    놀
    -0.76
    POSITIVE LOGITS
     midpoint
    1.66
     endpoint
    1.50
     points
    1.46
     intersection
    1.43
     CGPoint
    1.43
     endpoints
    1.40
     mid
    1.39
     center
    1.34
     point
    1.29
     middle
    1.27
    Activations Density 0.022%

    No Known Activations