© 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. 40-GEMMASCOPE-2-RES-262K
    7. 484
    Prev
    Next
    INDEX
    Explanations

    sorting lists and data

    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_40_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
    5
    0.46
    6
    0.43
    ONS
    0.41
     less
    0.41
     pon
    0.41
    ސް
    0.41
    ت
    0.41
    EMA
    0.41
    ->
    0.40
     magn
    0.40
    POSITIVE LOGITS
     сорти
    0.66
     sorting
    0.60
     sor
    0.59
     sorts
    0.56
    sortBy
    0.56
     sortBy
    0.56
    Sor
    0.55
    Sort
    0.55
    sort
    0.54
     Sorting
    0.54
    Activations Density 0.014%

    No Known Activations