© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5579
    Prev
    Next
    INDEX
    Explanations

    quant connect

    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_16k_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
    Benzoimidazol
    0.62
    绘
    0.58
    热水
    0.58
    ură
    0.57
    蓣
    0.55
     Campground
    0.55
    ów
    0.54
    ută
    0.54
    编码
    0.52
    ś
    0.52
    POSITIVE LOGITS
    投資
    1.02
     portfolios
    0.96
     portfolio
    0.94
     fund
    0.93
     investors
    0.92
     investment
    0.90
    基金
    0.87
     funds
    0.86
     fiduciary
    0.85
     Funds
    0.85
    Activations Density 0.189%

    No Known Activations