© 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. 92402
    Prev
    Next
    INDEX
    Explanations

    order status updates

    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
    atchi
    -0.79
    vanju
    -0.78
     člove
    -0.77
     infiltrated
    -0.71
     коллек
    -0.71
    就會
    -0.70
     Inves
    -0.68
    rosz
    -0.68
    をご覧ください
    -0.68
    图标
    -0.68
    POSITIVE LOGITS
     Nutt
    0.81
    OrderStatus
    0.78
     peng
    0.75
     Tk
    0.73
     customer
    0.73
    yscale
    0.72
     TPC
    0.72
    ʟ
    0.70
    書房
    0.69
     terape
    0.68
    Activations Density 0.018%

    No Known Activations