© 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. 34-GEMMASCOPE-RES-131K
    7. 49363
    Prev
    Next
    INDEX
    Explanations

    .Xaml namespace

    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_34/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
    σο
    -0.71
     GUN
    -0.70
     ترکی
    -0.69
     Erick
    -0.68
     skin
    -0.68
     Oppen
    -0.67
    ارت
    -0.66
    apj
    -0.66
     بين
    -0.66
     péri
    -0.66
    POSITIVE LOGITS
    ровень
    0.75
    hive
    0.73
    حص
    0.68
     Outputs
    0.68
    senz
    0.67
    tablissement
    0.66
     wollen
    0.65
    BPA
    0.65
     incul
    0.65
    onnay
    0.63
    Activations Density 0.058%

    No Known Activations