© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6672
    Prev
    Next
    INDEX
    Explanations

    market behavior drivers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     选择
    0.76
    鲷
    0.75
    防护
    0.74
     设计
    0.74
    玛
    0.74
    设施
    0.74
    贰百
    0.73
    兰
    0.73
     安装
    0.72
    邬
    0.72
    POSITIVE LOGITS
     bullish
    1.23
     bearish
    1.16
     macroeconomic
    0.97
     headwinds
    0.94
     investors
    0.93
     market
    0.93
     markets
    0.91
     forecasts
    0.89
     volatility
    0.89
     investor
    0.88
    Activations Density 0.167%

    No Known Activations