© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14662
    Prev
    Next
    INDEX
    Explanations

    sad emoticon

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

    The main thing this neuron does is detect numeric values (measurements, codes, dates, and other numbers).

    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
    耦合
    0.51
     coupling
    0.47
     первый
    0.47
    tron
    0.46
    coupling
    0.46
    িষ্ট
    0.45
    OfType
    0.45
    暱
    0.45
    cene
    0.45
    é
    0.44
    POSITIVE LOGITS
     ۱۹
    0.79
     dezelfde
    0.79
     ۹
    0.74
     ۱۴
    0.73
     ۲۰
    0.71
     XNUMX
    0.70
     hetzelfde
    0.68
     ۱۵
    0.68
     TikTok
    0.67
     Morbi
    0.67
    Activations Density 0.813%

    No Known Activations