© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66236
    Prev
    Next
    INDEX
    Explanations

    local development and storage

    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
    ↵
    -1.57
     lunghi
    -1.56
     Hacer
    -1.51
     historische
    -1.51
     quedará
    -1.46
     Jego
    -1.45
     nimmer
    -1.44
     maler
    -1.41
     què
    -1.40
     Sı
    -1.39
    POSITIVE LOGITS
    \
    1.88
    with
    1.83
    廂
    1.79
    。
    1.71
    orra
    1.62
    ;;
    1.61
    p
    1.59
    ;/
    1.59
     menghubungi
    1.56
    énage
    1.55
    Activations Density 0.064%

    No Known Activations