© 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. 94132
    Prev
    Next
    INDEX
    Explanations

    drones

    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
    sprung
    -0.93
     воин
    -0.91
    Sprint
    -0.89
     Earthquakes
    -0.86
     Bicycle
    -0.85
    Firefox
    -0.85
    Dress
    -0.84
     Automobile
    -0.84
     diner
    -0.83
     Earthquake
    -0.83
    POSITIVE LOGITS
     drone
    2.45
     drones
    2.06
     DJI
    1.95
     Drone
    1.85
    drone
    1.84
     flying
    1.76
    Drone
    1.73
     UAV
    1.67
     Drones
    1.62
     flight
    1.49
    Activations Density 0.024%

    No Known Activations