© 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. 93004
    Prev
    Next
    INDEX
    Explanations

    electricity transmission lines

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

    The neuron strongly activates on technical terms naming components or programs of electrical power infrastructure—especially phrases about electricity transmission networks, capacity, and related directives.

    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
    舷
    -0.83
     хок
    -0.80
     Eugenia
    -0.78
    ORT
    -0.72
    自行
    -0.71
    FileSystem
    -0.71
     curva
    -0.70
     hydrophilic
    -0.69
    LookAnd
    -0.68
     двигателя
    -0.68
    POSITIVE LOGITS
     transmission
    2.02
    Transmission
    1.64
     Transmission
    1.60
    transmission
    1.57
     transmit
    1.27
     transmitting
    1.26
     transmissions
    1.24
     transmis
    1.18
    transmit
    1.18
     TRANSMISSION
    1.17
    Activations Density 0.024%

    No Known Activations