© 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. 117
    Prev
    Next
    INDEX
    Explanations

    overlap or lapping

    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
    ;;)
    -1.72
    琑
    -1.64
    .
    -1.62
     الشهر
    -1.55
     vider
    -1.51
     This
    -1.49
     is
    -1.49
     publice
    -1.48
     priva
    -1.46
     vollständige
    -1.42
    POSITIVE LOGITS
     Ее
    1.71
     vying
    1.67
    METHODOLOGY
    1.66
    tekend
    1.63
     médaille
    1.62
     plupart
    1.62
     of
    1.57
    媖
    1.53
     greateſt
    1.52
    歃
    1.52
    Activations Density 0.017%

    No Known Activations