© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4211
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and symbols

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

    This neuron strongly activates on numeric tokens (including integers, decimals, and other number-like substrings).

    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
    ッピング
    0.77
    gena
    0.68
    疵
    0.68
    レクトリ
    0.64
    غراف
    0.64
    谑
    0.63
     الاشتراك
    0.63
    ार्मिक
    0.62
     حکمت
    0.62
    ahon
    0.61
    POSITIVE LOGITS
    :
    0.88
     çocuk
    0.81
     Çocuk
    0.78
     :
    0.77
    :(
    0.75
     Vậy
    0.73
     khối
    0.72
     chúng
    0.69
     tất
    0.67
     thì
    0.67
    Activations Density 0.002%

    No Known Activations