© 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. 58990
    Prev
    Next
    INDEX
    Explanations

    conic sections and surfaces

    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
    startAnimation
    -0.84
     irland
    -0.72
    TEP
    -0.72
     rectangles
    -0.68
     blues
    -0.66
    辩
    -0.66
    PIE
    -0.66
     rectangle
    -0.66
     oy
    -0.65
    OSP
    -0.65
    POSITIVE LOGITS
     cone
    1.28
     cones
    1.25
     parab
    1.13
    Cylinder
    1.09
     surfaces
    1.09
     Cone
    1.07
    cones
    1.04
    cone
    1.02
    cylinder
    1.02
     Surfaces
    1.01
    Activations Density 0.037%

    No Known Activations