© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116783
    Prev
    Next
    INDEX
    Explanations

    brushless DC motors

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on technical mentions of electrical machines—especially specific motor types (e.g. brushless, DC, synchronous, permanent-magnet motors) and related terminology.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Kenmerken
    -0.75
     manipulative
    -0.70
     Installer
    -0.70
     mecánico
    -0.68
    шни
    -0.68
    putString
    -0.68
     avven
    -0.68
     MECHANICAL
    -0.67
    朋友圈
    -0.67
    ineros
    -0.67
    POSITIVE LOGITS
     motors
    2.22
     motor
    1.80
     Motors
    1.57
    motors
    1.48
     brushless
    1.46
     electric
    1.29
     motores
    1.27
    motor
    1.26
    Motors
    1.21
     Brus
    1.20
    Activations Density 0.061%

    No Known Activations