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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9784
    Prev
    Next
    INDEX
    Explanations

    economic and financial trends

    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_262k_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
    科学家
    1.09
     让
    0.98
     马
    0.97
    鸟
    0.91
    荪
    0.91
    敌人
    0.91
     说
    0.89
    皞
    0.89
    闿
    0.89
    玛
    0.88
    POSITIVE LOGITS
     macroeconomic
    0.91
     volatility
    0.84
     liquidity
    0.84
    風險
    0.84
    risk
    0.83
     risk
    0.82
     geographies
    0.79
     headwinds
    0.79
    長期
    0.76
     underpinned
    0.75
    Activations Density 0.047%

    No Known Activations