© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6356
    Prev
    Next
    INDEX
    Explanations

    setting UI element attributes

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

    The neuron is sensitive to programming identifiers and API class or method names (e.g. capitalized code tokens like ViewGroup, XML, create, binding, name=).

    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
    emporary
    0.61
    Keychain
    0.54
    йом
    0.51
     choisissez
    0.50
    选择
    0.50
    앱
    0.49
    Choose
    0.48
    Choosing
    0.48
    選擇
    0.48
    美
    0.48
    POSITIVE LOGITS
    findViewById
    1.26
     findViewById
    1.26
    ViewById
    1.02
    findById
    0.80
    byId
    0.78
    ById
    0.77
     views
    0.77
     Views
    0.75
     found
    0.74
    ByID
    0.73
    Activations Density 0.010%

    No Known Activations