© 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. 22-GEMMASCOPE-RES-131K
    7. 67145
    Prev
    Next
    INDEX
    Explanations

    lamps and lighting

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

    The neuron is looking for technical discussion of lighting devices—especially lamps and LEDs—in patent-style or specification texts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     vermelhas
    -1.37
    aporation
    -1.29
    paccio
    -1.27
     ciertos
    -1.26
    翱
    -1.23
     complicaciones
    -1.23
    快要
    -1.22
     difíciles
    -1.21
    transporter
    -1.20
    院校
    -1.20
    POSITIVE LOGITS
    .
    1.30
     warung
    1.27
     الإعلام
    1.23
     Energía
    1.17
     Siglo
    1.13
     Rússia
    1.13
     Ngb
    1.11
    cE
    1.10
     teneb
    1.10
     проект
    1.05
    Activations Density 0.059%

    No Known Activations