© 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. 89732
    Prev
    Next
    INDEX
    Explanations

    under roofs and banners

    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
     masyarakat
    -0.81
    handlebars
    -0.77
     Jewish
    -0.75
    lifetime
    -0.71
    faced
    -0.71
    UST
    -0.71
     Handbook
    -0.71
     Hands
    -0.70
     разме
    -0.70
    يام
    -0.70
    POSITIVE LOGITS
     roof
    2.00
     umbrella
    1.79
     wing
    1.32
    roof
    1.25
     banner
    1.23
     roofs
    1.21
     wings
    1.20
     umbrellas
    1.12
     кры
    1.11
    umbrella
    1.09
    Activations Density 0.025%

    No Known Activations