© 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. 24-GEMMASCOPE-2-RES-16K
    7. 5494
    Prev
    Next
    INDEX
    Explanations

    following numbers and punctuation

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

    The neuron strongly activates on numeric tokens—digits, years, volume/page numbers, and other number sequences in reference citations.

    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_24_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
    פה
    0.82
    ités
    0.79
    rences
    0.79
    isNaN
    0.79
    eni
    0.78
    ز
    0.78
    ાદ
    0.78
    iet
    0.77
    éros
    0.77
    ުޅ
    0.76
    POSITIVE LOGITS
     വ
    0.86
     pelo
    0.80
     acompa
    0.75
     это
    0.75
    тический
    0.74
    Soup
    0.73
     apare
    0.73
     हिसाब
    0.73
     අ
    0.72
     treinamento
    0.72
    Activations Density 0.001%

    No Known Activations