© 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. 34-GEMMASCOPE-RES-131K
    7. 115668
    Prev
    Next
    INDEX
    Explanations

    Spring Boot applications

    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
     のみ
    -0.75
    岗
    -0.75
    bayern
    -0.71
    تاح
    -0.70
    ündung
    -0.70
    ZIONE
    -0.69
     skulle
    -0.68
     accomplish
    -0.68
     још
    -0.66
    kuh
    -0.66
    POSITIVE LOGITS
     application
    1.24
    Application
    1.15
     applications
    1.05
     立体
    1.04
     runner
    0.99
     aplikasi
    0.93
    起動
    0.93
     UIApplication
    0.91
     Application
    0.91
    application
    0.90
    Activations Density 0.002%

    No Known Activations