© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70525
    Prev
    Next
    INDEX
    Explanations

    A followed by numbers or letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’，
    -2.83
     "
    -2.30
    鹮
    -2.23
    ’
    -2.19
    vantaged
    -2.17
    ,’’
    -2.06
     洞
    -2.03
    睺
    -2.02
    阇
    -2.00
    𐑂
    -1.98
    POSITIVE LOGITS
     разные
    2.33
    [
    2.09
    也许
    1.88
     кно
    1.82
    瘣
    1.78
    )");
    1.73
     genannten
    1.73
    人的
    1.73
    BIÉN
    1.72
     DONT
    1.69
    Activations Density 0.012%

    No Known Activations