© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48099
    Prev
    Next
    INDEX
    Explanations

    rights reserved, description, weekly, window

    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
     worthy
    -0.83
    ведь
    -0.80
    unref
    -0.77
     peristiwa
    -0.75
    Mj
    -0.75
    alse
    -0.73
    eventually
    -0.72
     silen
    -0.72
     disorders
    -0.72
     essencial
    -0.71
    POSITIVE LOGITS
    Maximize
    0.96
     fixed
    0.77
    engarkan
    0.76
     Shade
    0.72
    fixed
    0.71
    Escape
    0.71
    vtk
    0.70
    Bitmap
    0.69
     Svensson
    0.68
    歩
    0.68
    Activations Density 0.007%

    No Known Activations