© 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. 6799
    Prev
    Next
    INDEX
    Explanations

    fluorescent lamps

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

    The neuron fires on technical terms for electromagnetic‐radiation sources—particularly ultraviolet (UV/UVR) exposure and various kinds of fluorescent lamps.

    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
     Tenga
    -0.80
     đức
    -0.80
    ومت
    -0.75
    🇸
    -0.75
    angal
    -0.75
    thé
    -0.73
    Telefon
    -0.71
    oopy
    -0.69
    UIButton
    -0.69
     Translator
    -0.68
    POSITIVE LOGITS
     fluorescent
    2.75
     Fluorescent
    2.09
     fluores
    2.06
     flores
    1.92
     fluorescence
    1.67
    orescent
    1.65
    蛍
    1.63
     tubes
    1.56
     tube
    1.46
    flu
    1.44
    Activations Density 0.029%

    No Known Activations