© 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. 65739
    Prev
    Next
    INDEX
    Explanations

    continuous wave or abbreviation

    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
     deur
    -0.84
    Throughput
    -0.81
    нительно
    -0.76
    embatan
    -0.73
    veness
    -0.73
     swoop
    -0.73
    NoStop
    -0.72
    subequations
    -0.72
     docente
    -0.72
    <0x9F>
    -0.72
    POSITIVE LOGITS
     CW
    1.32
    CW
    1.11
    备份
    0.79
     cw
    0.75
     coupled
    0.74
    ())));
    0.73
    cw
    0.72
    愼
    0.72
    tilha
    0.71
    untura
    0.70
    Activations Density 0.016%

    No Known Activations