© 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. 34-GEMMASCOPE-RES-131K
    7. 78245
    Prev
    Next
    INDEX
    Explanations

    meta charset utf-8/UTF-8

    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_34/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
    cnn
    -0.76
    Michigan
    -0.76
     cairan
    -0.70
     Michigan
    -0.69
     cytoplasm
    -0.68
    tilhar
    -0.68
     FPGA
    -0.68
     Floor
    -0.68
    DataAccess
    -0.67
     限
    -0.67
    POSITIVE LOGITS
     UTF
    3.16
     encoding
    2.97
    UTF
    2.75
    encoding
    2.61
     utf
    2.52
     Encoding
    2.42
     charset
    2.42
    utf
    2.41
    Encoding
    2.38
    charset
    2.36
    Activations Density 0.179%

    No Known Activations