© 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. 53898
    Prev
    Next
    INDEX
    Explanations

    brokerage business

    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
     ház
    -0.72
    Product
    -0.72
    спорти
    -0.70
    beve
    -0.70
    巨
    -0.69
    culo
    -0.69
    booking
    -0.68
    ठ
    -0.68
     homestead
    -0.68
    lización
    -0.68
    POSITIVE LOGITS
     broker
    1.98
     brokers
    1.91
     brokerage
    1.81
     Broker
    1.80
     Brokers
    1.64
    broker
    1.45
    Broker
    1.40
    brokers
    1.22
     listings
    1.07
     Exit
    1.05
    Activations Density 0.017%

    No Known Activations