© 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. 123105
    Prev
    Next
    INDEX
    Explanations

    threshold, pay, planning, ban, wait

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

    price and placeholders

    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
    である
    0.52
    运
    0.50
    工作人员
    0.50
    們
    0.50
    游戏
    0.49
    计算机
    0.48
    瑞
    0.47
    丛
    0.47
    ędzy
    0.46
    らしく
    0.46
    POSITIVE LOGITS
     priced
    0.60
     цена
    0.58
     कीमतों
    0.58
     prices
    0.55
     harga
    0.55
    ដើម្បី
    0.55
     investment
    0.54
     ដើម្បី
    0.54
     цену
    0.53
     unscrupulous
    0.52
    Activations Density 0.001%

    No Known Activations