© 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. 89911
    Prev
    Next
    INDEX
    Explanations

    MPI and parallel computing

    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
     влади
    -0.81
    ONSO
    -0.76
    Export
    -0.73
     KISS
    -0.73
    饵
    -0.72
     APPLY
    -0.71
     Helsinki
    -0.71
    TRIBUTION
    -0.69
    enca
    -0.68
     breastfeeding
    -0.68
    POSITIVE LOGITS
     MPI
    0.97
    ृत
    0.94
     mpi
    0.89
    יוון
    0.84
    upc
    0.84
    mpi
    0.84
     ラウンド
    0.78
    ۃ
    0.78
    Petsc
    0.77
    olda
    0.76
    Activations Density 0.017%

    No Known Activations