© 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. 55750
    Prev
    Next
    INDEX
    Explanations

    Microsoft Lumia phones

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

    The neuron fires on mentions of Windows Phone (and related Lumia) product names and version numbers (e.g. “Phone,” “7,” “Mango,” “8,” etc.).

    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
    
    -0.82
    ęty
    -0.81
    abro
    -0.77
    olsom
    -0.75
     combinado
    -0.75
    🥠
    -0.73
     artyku
    -0.72
    jobb
    -0.72
     magnético
    -0.71
    penalty
    -0.70
    POSITIVE LOGITS
     Lumia
    1.55
     Microsoft
    1.31
    Microsoft
    1.23
     Nokia
    1.13
    microsoft
    1.04
     WP
    0.95
    微软
    0.94
     wp
    0.93
     GDR
    0.93
     Marketplace
    0.91
    Activations Density 0.049%

    No Known Activations