© 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. 54288
    Prev
    Next
    INDEX
    Explanations

    money market funds

    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
    Stock
    -0.82
    DoesNotExist
    -0.80
    天文
    -0.77
    STOCK
    -0.71
    ROS
    -0.71
    DOCX
    -0.71
    对不起
    -0.68
    stock
    -0.68
     公
    -0.67
    gidos
    -0.67
    POSITIVE LOGITS
     money
    1.11
     short
    0.94
     overnight
    0.93
    money
    0.85
     breaking
    0.85
    unia
    0.84
     Money
    0.84
    breaking
    0.83
     liquid
    0.82
    zem
    0.82
    Activations Density 0.014%

    No Known Activations