© 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. 59060
    Prev
    Next
    INDEX
    Explanations

    code function definitions

    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
     parfüm
    -2.78
     sokak
    -2.64
    絝
    -2.45
     dön
    -2.39
     trastorno
    -2.38
     parfü
    -2.36
    窳
    -2.33
    ㌧
    -2.31
     ancillary
    -2.30
     eficientes
    -2.28
    POSITIVE LOGITS
    The
    2.83
    .
    2.67
    z
    2.41
    the
    2.38
    0
    2.33
    ”
    2.30
    which
    2.22
    i
    2.19
    +
    2.14
    ’
    2.14
    Activations Density 0.011%

    No Known Activations