© 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. 73474
    Prev
    Next
    INDEX
    Explanations

    shelton, mahogany, toothbrush, shale, Bethel

    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
     "
    -3.02
     ----
    -2.80
     -----
    -2.77
     "*
    -2.52
     ,"
    -2.50
     '"
    -2.50
    ні
    -2.48
    恹
    -2.47
     abject
    -2.47
     {"
    -2.47
    POSITIVE LOGITS
    {
    2.84
    趼
    2.80
    –
    2.75
    ;
    2.69
    .’
    2.67
    ’,
    2.53
     nearing
    2.44
     striving
    2.34
    酲
    2.31
    1
    2.28
    Activations Density 0.003%

    No Known Activations