© 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. 11852
    Prev
    Next
    INDEX
    Explanations

    your role or organization

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

    The neuron is triggered by numeric tokens (quantities, percentages, measurements, and other number-like 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_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
    𝘦
    0.83
    iciaire
    0.78
    暂停
    0.77
    颚
    0.76
    惆
    0.73
    𝘵
    0.73
    SHALL
    0.72
    𝑡
    0.70
    بری
    0.69
    ميل
    0.69
    POSITIVE LOGITS
     распоря
    0.78
     бө
    0.76
     ਦਵਾਈ
    0.73
    א
    0.72
    yclerView
    0.71
    ש
    0.70
     desempeñ
    0.68
     доля
    0.68
    দ্‌
    0.67
    кая
    0.67
    Activations Density 0.000%

    No Known Activations