© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 153921
    Prev
    Next
    INDEX
    Explanations

    options, futures, and derivatives

    np_acts-logits-general · gemini-2.5-flash-lite

    options trading and hedging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    动脉
    0.52
    MSFont
    0.49
     cæ
    0.48
     hải
    0.47
    墓志
    0.46
    鲶
    0.46
     జా
    0.46
    鸬
    0.45
    睐
    0.44
    swürdig
    0.44
    POSITIVE LOGITS
     hedging
    0.68
     futures
    0.61
     expiry
    0.59
     derivatives
    0.58
     hedges
    0.57
     derivative
    0.54
    Futures
    0.53
    衍生
    0.53
     hed
    0.52
     commodities
    0.52
    Activations Density 0.166%

    No Known Activations