© 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. 46917
    Prev
    Next
    INDEX
    Explanations

    beginner's guidemajority ofone health optionbeginner's yoga

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

    beginner's guides and introductions

    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
    써
    0.48
     Marxist
    0.45
     หนึ่ง
    0.45
    អ្វី
    0.45
     値
    0.44
     Vedi
    0.44
     동시에
    0.44
    фикации
    0.43
     Leit
    0.43
     Linie
    0.43
    POSITIVE LOGITS
     acetaminophen
    0.52
     pharmacokinetic
    0.48
    ة
    0.46
    简单的
    0.45
    اشة
    0.45
     corrected
    0.44
    rası
    0.44
    toj
    0.43
    鸥
    0.43
    巴
    0.43
    Activations Density 0.000%

    No Known Activations