© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10101
    Prev
    Next
    INDEX
    Explanations

    all variants, lists, or parts

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

    The neuron strongly activates on standalone labels or headings that introduce major steps or sections in a procedure (e.g. “Final request,” “process to access voluntary assisted dying,” “technical diving,” “coconut oil detox,” “blooming tea,” “medicine”).

    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
     Ironically
    0.92
     시장
    0.79
    Ironically
    0.77
    skoj
    0.75
     市場
    0.75
     ostensibly
    0.75
     산업
    0.74
     เมือง
    0.74
     उद्यम
    0.72
     이후
    0.71
    POSITIVE LOGITS
     semua
    0.98
     fases
    0.97
     всех
    0.95
     ಎಲ್ಲಾ
    0.90
     flowchart
    0.88
     всіх
    0.87
     dependiendo
    0.84
     каждого
    0.84
    すべての
    0.83
     todas
    0.82
    Activations Density 0.049%

    No Known Activations