© 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
    2. Gemma-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 5479
    Prev
    Next
    INDEX
    Explanations

    tables, lists, and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
     report
    0.67
     spreadsheet
    0.63
     x
    0.63
    */
    0.57
     X
    0.57
     REPORT
    0.57
     spreadsheets
    0.57
     Excel
    0.55
     template
    0.54
     rows
    0.54
    POSITIVE LOGITS
     {|
    0.73
    ccccc
    0.71
    lcc
    0.71
     अभिव्य
    0.69
    सीसी
    0.67
    CCCC
    0.66
     |”
    0.62
     திரு
    0.61
    ccc
    0.60
     Leider
    0.59
    Activations Density 0.043%

    No Known Activations