© 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. 84840
    Prev
    Next
    INDEX
    Explanations

    Windows Phone UI elements and code

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

    This neuron activates on XML markup syntax (angle-bracketed tags and namespace/attribute declarations).

    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
     ří
    -0.86
     rút
    -0.79
    ایع
    -0.74
    仡
    -0.73
    cetype
    -0.71
    最小
    -0.71
     vyd
    -0.71
    discriminator
    -0.71
    гава
    -0.71
     considers
    -0.71
    POSITIVE LOGITS
    AppBar
    1.17
     Lumia
    1.16
    Panorama
    1.06
     WP
    1.02
     AppBar
    0.95
     Panorama
    0.90
     Pivot
    0.89
    MainPage
    0.89
     Nokia
    0.88
     zune
    0.87
    Activations Density 0.100%

    No Known Activations