© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102803
    Prev
    Next
    INDEX
    Explanations

    high pressure gas discharge lamp

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

    The neuron detects technical patent jargon, especially lighting‐and‐lamp engineering terms (e.g. ballast, power­ing, gas discharge, high-pressure, ambient light control).

    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
    跖
    -0.72
    μένος
    -0.71
    ולי
    -0.71
    сите
    -0.70
    jdons
    -0.69
    PMailer
    -0.69
     establecimiento
    -0.68
     dream
    -0.68
    giaan
    -0.67
    PURPOSE
    -0.67
    POSITIVE LOGITS
    ilets
    0.83
     driver
    0.81
     depreciation
    0.81
     EMERGENCY
    0.79
     lumen
    0.79
     lum
    0.79
    ダウンロード
    0.79
     volant
    0.79
    Emergency
    0.78
     piment
    0.78
    Activations Density 0.016%

    No Known Activations