© 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. 38587
    Prev
    Next
    INDEX
    Explanations

    themed attractions and events

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

    This neuron fires on multi‐word proper names—especially resort, hotel, and destination titles (e.g. “Disneyland Paris,” “Disney’s Hotel New York – The Art of Marvel”).

    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
     Locally
    -0.93
    न्न
    -0.82
     nécessaire
    -0.81
     Analyzing
    -0.79
    gründet
    -0.79
     PANEL
    -0.78
    ownie
    -0.77
    幸いです
    -0.77
    mphony
    -0.76
    locally
    -0.76
    POSITIVE LOGITS
     areas
    0.96
     themed
    0.83
     ショップ
    0.80
    エリア
    0.77
     Main
    0.76
     shops
    0.74
     show
    0.74
    Cri
    0.73
    themed
    0.72
    cornerRadius
    0.71
    Activations Density 0.007%

    No Known Activations