© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7618
    Prev
    Next
    INDEX
    Explanations

    XML/UI elements and attributes

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

    This neuron detects mentions of Android framework API class and component names (e.g. Android architecture components, ContentResolver, CursorLoader).

    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
    initializeApp
    0.59
     configuring
    0.53
     evident
    0.50
     functioned
    0.50
    Connected
    0.50
    бка
    0.50
    停留
    0.50
    銚
    0.50
    ஜ்
    0.49
    区块链
    0.49
    POSITIVE LOGITS
     Tint
    0.86
     RecyclerView
    0.76
     itemView
    0.76
    Tint
    0.74
     TabLayout
    0.74
     Compat
    0.72
     ViewGroup
    0.71
    ViewGroup
    0.70
     AppCompat
    0.66
    Compat
    0.65
    Activations Density 0.017%

    No Known Activations