© 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. 176
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is spot references to Android platform APIs and components (e.g. class and method names like Context, getContentResolver/ContentResolver, AIDL, onBind, etc.).

    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
     hypergeometric
    0.70
    ळख
    0.69
     zbior
    0.65
     diminution
    0.64
     unregulated
    0.64
    व्हाण
    0.62
     asbestos
    0.60
    辋
    0.60
     potting
    0.59
     ډول
    0.58
    POSITIVE LOGITS
    android
    1.66
     Android
    1.65
     AppCompat
    1.65
    Android
    1.64
     android
    1.63
    androidx
    1.63
    AppCompat
    1.52
     androidx
    1.52
    MainActivity
    1.52
     MainActivity
    1.48
    Activations Density 0.010%

    No Known Activations