© 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. 65341
    Prev
    Next
    INDEX
    Explanations

    switch plateArchive forKinetics ofQ:

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

    The neuron detects technical terms related to electrical wall‐plate hardware (e.g. “wall,” “plates,” “switch,” “outlet,” “cover,” etc.) in patent-style descriptions.

    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
     piensa
    -0.73
     muffler
    -0.72
     amenazas
    -0.71
    เกิน
    -0.71
    ikuti
    -0.71
    循環
    -0.70
     comic
    -0.70
    Comic
    -0.70
    NavController
    -0.70
     stanno
    -0.69
    POSITIVE LOGITS
     wall
    1.03
     dimmer
    1.02
     drywall
    0.90
     flush
    0.88
     switches
    0.87
     Wall
    0.85
    wall
    0.84
     Flush
    0.82
     Clips
    0.82
     switch
    0.80
    Activations Density 0.018%

    No Known Activations