© 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. 91724
    Prev
    Next
    INDEX
    Explanations

    WPF UI elements

    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
    MainPage
    -0.85
    ropa
    -0.80
    AppBar
    -0.74
    ÈS
    -0.73
    unea
    -0.73
    DataInputStream
    -0.71
     Bani
    -0.71
    daos
    -0.70
     MainPage
    -0.70
     поток
    -0.70
    POSITIVE LOGITS
     Iowa
    0.81
    Iowa
    0.77
    Interop
    0.77
     apertura
    0.72
    こんな
    0.71
    刪除
    0.70
     प्रकार
    0.68
    Problems
    0.68
     Aplikasi
    0.66
    மா
    0.66
    Activations Density 0.018%

    No Known Activations