© 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. 1290
    Prev
    Next
    INDEX
    Explanations

    font and creation date

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

    The neuron activates on numeric tokens (especially decimal numbers), effectively detecting numbers in the text.

    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
    czeniu
    0.64
    jumlah
    0.64
    aggregation
    0.63
    межу
    0.63
    getLevel
    0.60
    鏝
    0.60
    ’
    0.60
    વાર
    0.60
    čila
    0.60
    collectionView
    0.59
    POSITIVE LOGITS
    ↵↵↵
    0.88
    ↵↵↵↵
    0.80
    ↵
    0.77
     |
    0.76
    ↵↵↵↵↵↵
    0.75
     …
    0.75
    ↵↵↵↵↵
    0.74
     Datenschutz
    0.74
     ›
    0.74
     Yogyakarta
    0.73
    Activations Density 0.161%

    No Known Activations