© 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. 66310
    Prev
    Next
    INDEX
    Explanations

    C/C++ declarations

    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
     Varianten
    -0.94
     usah
    -0.90
    yng
    -0.88
     to
    -0.82
     igreja
    -0.82
     Sorten
    -0.81
     DISPOSAL
    -0.81
     oração
    -0.80
    agency
    -0.79
     aseguran
    -0.78
    POSITIVE LOGITS
     {
    0.85
     {//
    0.82
     clor
    0.78
     bestseller
    0.77
     حالا
    0.77
     ".$
    0.76
     OVA
    0.76
    anniversaire
    0.75
     organi
    0.75
    odly
    0.75
    Activations Density 0.001%

    No Known Activations