© 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. 11746
    Prev
    Next
    INDEX
    Explanations

    SAP UI components and frameworks

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

    The neuron fires on numeric tokens—especially standalone numbers or numeric literals (e.g. integers or floating-point values).

    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
    Carn
    0.59
     रणवीर
    0.57
    貔
    0.56
    NR
    0.54
    nus
    0.54
     তাড়
    0.54
    Dockerfile
    0.53
    晩
    0.53
     এজেন্ট
    0.53
    慢慢
    0.52
    POSITIVE LOGITS
     xhr
    1.02
     widget
    0.90
     widgets
    0.89
    xhr
    0.81
     collectionView
    0.79
     jQuery
    0.78
     jquery
    0.77
    CollectionView
    0.76
    .$.
    0.72
     Widget
    0.69
    Activations Density 0.020%

    No Known Activations