© 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. 65437
    Prev
    Next
    INDEX
    Explanations

    build software

    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
    ྅
    -1.84
     広場
    -1.74
    Ꮴ
    -1.65
     abbiano
    -1.56
     pieni
    -1.55
    магазин
    -1.55
    مدل
    -1.52
     polecam
    -1.49
     haki
    -1.48
     variadas
    -1.47
    POSITIVE LOGITS
    build
    2.06
     for
    2.02
     a
    1.97
     with
    1.97
     on
    1.86
     build
    1.85
     in
    1.80
     In
    1.70
    builder
    1.66
    ,
    1.58
    Activations Density 0.082%

    No Known Activations