© 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. 38230
    Prev
    Next
    INDEX
    Explanations

    public class MainActivity extends Activity

    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
     hukuman
    -0.81
    癜
    -0.81
    pisode
    -0.81
     Técnico
    -0.79
    czar
    -0.79
     Frieden
    -0.77
    volvo
    -0.76
     madrugada
    -0.75
    tabIndex
    -0.75
    diente
    -0.75
    POSITIVE LOGITS
     MainActivity
    2.81
    MainActivity
    2.52
     Main
    1.85
     main
    1.70
     MainWindow
    1.65
    main
    1.63
    Main
    1.61
    MainWindow
    1.45
     MAIN
    1.35
    MAIN
    1.30
    Activations Density 0.022%

    No Known Activations