© 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. 92478
    Prev
    Next
    INDEX
    Explanations

    network traffic engineering and measurement

    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
    Ở
    -0.79
    edì
    -0.76
     SEGU
    -0.73
    elance
    -0.72
    udic
    -0.71
    usb
    -0.69
    接口
    -0.69
    тури
    -0.69
     سے
    -0.69
    ѣ
    -0.68
    POSITIVE LOGITS
     Internet
    1.46
     measurement
    1.27
    measurement
    1.26
     Measurement
    1.25
    Measurement
    1.24
     router
    1.11
     Интернет
    1.09
     measurements
    1.05
    Internet
    1.05
    Measurements
    1.03
    Activations Density 0.061%

    No Known Activations