© 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. 10-GEMMASCOPE-RES-131K
    7. 65332
    Prev
    Next
    INDEX
    Explanations

    JSON object keys and greetings

    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
    ↵
    -2.19
    ,”
    -1.83
    You
    -1.78
     "
    -1.69
    </strong>
    -1.65
    is
    -1.63
    ”，
    -1.59
    趼
    -1.57
    ungguhnya
    -1.53
    蕺
    -1.53
    POSITIVE LOGITS
     muun
    1.99
     {\
    1.76
     erila
    1.67
     ส์
    1.66
     usato
    1.66
    
    1.63
    ccccc
    1.59
     mankind
    1.59
     esferas
    1.57
     taşlı
    1.55
    Activations Density 0.015%

    No Known Activations