© 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. 48985
    Prev
    Next
    INDEX
    Explanations

    Napa Valley and Sonoma Raceway

    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
     Malaga
    -0.97
     Gino
    -0.83
     uterine
    -0.80
     Málaga
    -0.79
     Andalu
    -0.78
     ank
    -0.77
    шер
    -0.76
     Bucs
    -0.74
    cedor
    -0.74
    anterior
    -0.74
    POSITIVE LOGITS
     Napa
    1.16
     Employers
    0.71
    çe
    0.69
     Puli
    0.68
    (||
    0.66
     Silverado
    0.66
    пуска
    0.65
    achute
    0.65
     çev
    0.64
    :^{
    0.64
    Activations Density 0.028%

    No Known Activations