© 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. 57826
    Prev
    Next
    INDEX
    Explanations

    surface area

    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
    ソリン
    -0.77
    ्रो
    -0.75
    Execu
    -0.70
    ToolStripButton
    -0.69
     spits
    -0.69
    dant
    -0.68
     выполнять
    -0.68
     async
    -0.68
    invite
    -0.67
     Defend
    -0.67
    POSITIVE LOGITS
     surface
    2.69
    surface
    2.16
     Surface
    2.09
     surfaces
    2.00
    Surface
    1.93
     поверхности
    1.84
     SURFACE
    1.66
    urface
    1.56
     Surfaces
    1.52
     exposed
    1.51
    Activations Density 0.054%

    No Known Activations