© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58070
    Prev
    Next
    INDEX
    Explanations

    financial risk and capital

    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
    Price
    -0.93
     price
    -0.91
     precio
    -0.87
    price
    -0.84
     Price
    -0.82
    øde
    -0.81
     PRICE
    -0.79
    buz
    -0.76
    setPrice
    -0.76
    滞
    -0.75
    POSITIVE LOGITS
     risk
    1.52
     risked
    1.40
    資金
    1.39
     risking
    1.38
     capital
    1.30
    Risk
    1.28
    risk
    1.28
    capital
    1.21
     Risk
    1.11
     capitale
    1.03
    Activations Density 0.012%

    No Known Activations