© 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. 73841
    Prev
    Next
    INDEX
    Explanations

    android getSystemService

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

    The neuron is triggered by occurrences of “Manager” (especially Android system‐service manager classes and related calls).

    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
    δε
    -0.86
     брюки
    -0.81
    SMA
    -0.79
     организа
    -0.77
     SMA
    -0.76
     leg
    -0.75
     verarbeitet
    -0.74
     vandens
    -0.72
    xis
    -0.70
     corridors
    -0.69
    POSITIVE LOGITS
    getSystemService
    1.82
     getSystem
    1.64
     system
    1.49
     services
    1.47
     Services
    1.15
     систем
    1.13
     sistem
    1.09
     System
    1.07
    SYSTEM
    1.06
    system
    1.05
    Activations Density 0.016%

    No Known Activations