© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 24125
    Prev
    Next
    INDEX
    Explanations

    sorting data or collections

    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_all/layer_41_width_262k_l0_big
    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
    在这种
    0.42
    racción
    0.37
     меку
    0.35
     teslim
    0.35
    軾
    0.35
    тации
    0.34
    বারিক
    0.34
    ꧂
    0.34
    asında
    0.34
     частей
    0.34
    POSITIVE LOGITS
     sorted
    2.25
    sorted
    2.09
     Sorted
    1.84
    Sorted
    1.82
     sorting
    1.69
    排序
    1.62
     arranged
    1.55
    sortBy
    1.53
     Sorting
    1.50
     сорти
    1.48
    Activations Density 0.003%

    No Known Activations