© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31642
    Prev
    Next
    INDEX
    Explanations

    app development context

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects app-lifecycle delegate method signatures (e.g. applicationDidFinishLaunching(_:), applicationDidBecomeActive(_:) and similar UIApplicationDelegate declarations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ňte
    -0.87
     Ке
    -0.83
     K
    -0.82
     devi
    -0.81
    sif
    -0.79
    ͪ
    -0.78
     k
    -0.76
    
    -0.73
     svil
    -0.73
     OFF
    -0.72
    POSITIVE LOGITS
     poslední
    0.88
    昔から
    0.88
    illoma
    0.84
    pernic
    0.84
     soutě
    0.82
     韓国
    0.82
     cóc
    0.80
    حال
    0.78
     referido
    0.77
     thorough
    0.77
    Activations Density 0.015%

    No Known Activations