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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 46673
    Prev
    Next
    INDEX
    Explanations

    Stored XSS

    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_16_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
    <unused1071>
    0.66
    日曜
    0.64
    মতী
    0.61
    ﾝ
    0.61
    ند
    0.60
    <unused1112>
    0.59
     Asalamualaikum
    0.58
     sbParams
    0.57
    шон
    0.57
    ра
    0.56
    POSITIVE LOGITS
    t
    0.80
    o
    0.76
    0.75
     T
    0.73
    é
    0.72
     S
    0.72
     X
    0.69
     A
    0.68
     The
    0.68
     R
    0.67
    Activations Density 0.000%

    No Known Activations