© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1578
    Prev
    Next
    INDEX
    Explanations

    network connection or data transmission

    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_10/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
    彣
    -1.69
    そういえば
    -1.68
     ギャラリー
    -1.66
    羕
    -1.66
    ある
    -1.65
    .’
    -1.60
     damaligen
    -1.57
     passenden
    -1.57
     kostenlosen
    -1.55
     geschlagen
    -1.52
    POSITIVE LOGITS
     of
    1.94
    UMENTO
    1.79
    。"
    1.62
    datable
    1.61
     طریق
    1.57
    、
    1.54
     soportar
    1.53
    纏
    1.53
    ка
    1.52
    gages
    1.52
    Activations Density 0.010%

    No Known Activations