© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7940
    Prev
    Next
    INDEX
    Explanations

    state management and background tasks

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

    The neuron fires on mentions of Android’s Architecture Components (e.g. “architecture components,” “Room”) and related testing/mock infrastructure.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    íso
    0.54
    prototype
    0.53
    Jest
    0.50
    సర్
    0.50
    IOS
    0.50
    Houston
    0.50
    址
    0.50
    TEL
    0.49
    amit
    0.49
    <0x04>
    0.48
    POSITIVE LOGITS
    ViewModel
    0.84
    LiveData
    0.84
     ViewModel
    0.80
    viewModel
    0.75
     viewModel
    0.74
     lived
    0.69
    ViewModels
    0.68
    databinding
    0.67
    lived
    0.66
     lifecycle
    0.66
    Activations Density 0.006%

    No Known Activations