© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45032
    Prev
    Next
    INDEX
    Explanations

    billions of dollars, euros, people, or copies

    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
    もありました
    -2.33
     have
    -2.28
    諳
    -2.20
    或
    -2.17
    ꯵
    -2.14
    and
    -2.14
    鄖
    -2.14
    Ꮏ
    -2.13
    咘
    -2.13
    or
    -2.13
    POSITIVE LOGITS
    .
    2.92
    ,"
    2.64
    ل
    2.50
     of
    2.48
    u
    2.22
    )'
    2.13
    '
    2.11
     он
    2.08
    ://
    2.05
    NUMX
    2.05
    Activations Density 0.005%

    No Known Activations