© 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. 22-GEMMASCOPE-RES-131K
    7. 9337
    Prev
    Next
    INDEX
    Explanations

    standard output

    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_22/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
    кен
    -0.80
    ísima
    -0.80
     lainnya
    -0.79
    knn
    -0.79
    dtos
    -0.78
     from
    -0.78
    撄
    -0.78
    ്‍
    -0.78
     erop
    -0.77
    그는
    -0.77
    POSITIVE LOGITS
    kyrie
    0.93
     Leute
    0.84
     balance
    0.81
    olson
    0.78
    herbe
    0.77
     ")";
    0.75
     Balance
    0.74
    各种
    0.74
     probable
    0.74
     Post
    0.73
    Activations Density 0.028%

    No Known Activations