© 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. 6971
    Prev
    Next
    INDEX
    Explanations

    licensed under the Apache License

    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
     step
    -0.75
    URER
    -0.71
    step
    -0.71
    Military
    -0.71
    bui
    -0.70
    alium
    -0.68
     Military
    -0.67
    Δ
    -0.67
    出现
    -0.66
    nguyen
    -0.66
    POSITIVE LOGITS
     酒店
    0.70
     DPI
    0.67
     CFM
    0.64
     Tenant
    0.62
     vaca
    0.62
     Cellar
    0.62
     peo
    0.61
     cappella
    0.61
     notches
    0.61
     начинается
    0.60
    Activations Density 0.070%

    No Known Activations