© 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. 15350
    Prev
    Next
    INDEX
    Explanations

    C++ code headers and definitions

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

    The neuron fires strongly on lone, initial capitalized words that serve as section headings or titles.

    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
     作者
    0.90
     Physiology
    0.81
    aturday
    0.80
     کافی
    0.79
    ━━━━━━━━
    0.78
    AYLOR
    0.78
     lymphoid
    0.75
     نداشت
    0.75
    <0xA3>
    0.75
    ları
    0.75
    POSITIVE LOGITS
    in
    1.18
    на
    0.93
    houses
    0.90
    an
    0.88
    но
    0.88
    ю
    0.86
    ل
    0.86
    es
    0.80
    ein
    0.80
    er
    0.79
    Activations Density 0.000%

    No Known Activations