© 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. 71715
    Prev
    Next
    INDEX
    Explanations

    code blocks with delimiters

    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
    ‘
    -1.90
    “
    -1.68
    "
    -1.66
     seems
    -1.63
    k
    -1.62
    You
    -1.56
    They
    -1.52
     had
    -1.51
    (￣
    -1.49
    All
    -1.48
    POSITIVE LOGITS
    ꜆
    1.80
     defying
    1.75
     citroen
    1.72
    salms
    1.69
    ᐕ
    1.67
     GETTING
    1.66
     geel
    1.64
    ｊ
    1.63
    縢
    1.63
    푐
    1.62
    Activations Density 0.002%

    No Known Activations