© 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. 55834
    Prev
    Next
    INDEX
    Explanations

    NFS, RPC, procedures

    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
     си
    -0.81
    SDL
    -0.81
    wortet
    -0.75
    ecore
    -0.75
     Mam
    -0.75
     сигна
    -0.74
     USB
    -0.74
    fib
    -0.73
    Mam
    -0.72
    тового
    -0.71
    POSITIVE LOGITS
     NFS
    1.02
    xdr
    0.89
     Procedures
    0.87
     SUNY
    0.85
    CLIENT
    0.85
     RPC
    0.81
     CLIENT
    0.81
     procedures
    0.79
    procedures
    0.78
    Procedures
    0.76
    Activations Density 0.056%

    No Known Activations