© 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. 109541
    Prev
    Next
    INDEX
    Explanations

    historic downtown shops

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Landfill
    -0.95
     mépris
    -0.89
     Dynasty
    -0.89
    icago
    -0.85
    ֻ
    -0.84
     Clubhouse
    -0.82
    وحة
    -0.81
    لاثة
    -0.81
    Gardening
    -0.81
    ສ
    -0.80
    POSITIVE LOGITS
     downtown
    2.30
    Historic
    1.72
     historic
    1.59
     Historic
    1.59
    downtown
    1.57
     town
    1.48
    Downtown
    1.48
     merchants
    1.46
     businesses
    1.44
     shops
    1.44
    Activations Density 0.047%

    No Known Activations