© 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. 218347
    Prev
    Next
    INDEX
    Explanations

    Shen Yun

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

    explicit sexual content

    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
    le
    0.50
    (
    0.48
    ut
    0.47
    st
    0.47
    지가
    0.47
    ز
    0.45
    ées
    0.45
    ତ
    0.45
    nz
    0.45
    nem
    0.43
    POSITIVE LOGITS
     อังกฤษ
    0.53
     wọn
    0.48
     parceria
    0.46
     kanilang
    0.46
     njihov
    0.46
    ニュース
    0.45
     sasan
    0.44
     இதனால்
    0.44
     eſ
    0.44
     decedent
    0.44
    Activations Density 0.001%

    No Known Activations