© 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. 13277
    Prev
    Next
    INDEX
    Explanations

    code structure and imports

    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
     now
    -0.88
     roligt
    -0.87
     vatten
    -0.82
     $^{
    -0.80
    ционная
    -0.79
    >|
    -0.77
    士尼
    -0.77
     finally
    -0.75
    نمای
    -0.75
    eres
    -0.74
    POSITIVE LOGITS
    test
    0.97
    ftest
    0.94
     Bahkan
    0.92
    📫
    0.88
    tst
    0.84
    갔
    0.83
    addTab
    0.83
     punggung
    0.83
     sute
    0.83
     fiori
    0.82
    Activations Density 0.000%

    No Known Activations