© 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. 45597
    Prev
    Next
    INDEX
    Explanations

    drone or quadcopter

    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
    利的
    -0.81
    adel
    -0.77
    pstmt
    -0.75
    joints
    -0.74
     Oncol
    -0.73
    扈
    -0.73
    zweck
    -0.73
    alb
    -0.72
    chafft
    -0.71
    ondern
    -0.69
    POSITIVE LOGITS
     drones
    1.62
     drone
    1.60
     quad
    1.25
    quad
    1.10
    drone
    1.05
     Drone
    1.05
     Quad
    1.01
     quads
    0.97
     DJI
    0.97
    Quad
    0.94
    Activations Density 0.032%

    No Known Activations