© 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. 45296
    Prev
    Next
    INDEX
    Explanations

    software paths and notices

    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
    \
    -2.89
     
    -2.88
    '
    -2.77
    ’
    -2.39
     '
    -2.39
    鼉
    -2.36
    {
    -2.36
     Of
    -2.30
    \'
    -2.23
     \
    -2.17
    POSITIVE LOGITS
    媖
    2.91
    .
    2.77
    the
    2.48
    but
    2.47
    for
    2.44
    玧
    2.39
    The
    2.33
    媄
    2.28
    弍
    2.28
    ztes
    2.27
    Activations Density 0.042%

    No Known Activations