© 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. 63509
    Prev
    Next
    INDEX
    Explanations

    surfaces, curves, and polynomials

    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
    ynie
    -0.83
    angue
    -0.81
     screenWidth
    -0.80
     Wett
    -0.73
     линей
    -0.73
    sendKeys
    -0.73
    jini
    -0.70
     Dissent
    -0.69
     Maciej
    -0.68
    рам
    -0.68
    POSITIVE LOGITS
     surface
    2.20
     surfaces
    1.97
    surface
    1.78
     Surface
    1.77
    Surface
    1.66
     contour
    1.59
     Surfaces
    1.42
    surf
    1.38
     поверхности
    1.38
     SURFACE
    1.36
    Activations Density 0.037%

    No Known Activations