© 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. 31-GEMMASCOPE-2-RES-16K
    7. 530
    Prev
    Next
    INDEX
    Explanations

    Xiaoling Subdistrict

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

    The neuron fires on tokens that begin sentences or are capitalized (proper nouns and sentence-initial words).

    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_31_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
     stycz
    0.60
    桝
    0.58
    鞆
    0.57
     joggers
    0.56
     konkre
    0.55
     متنوع
    0.55
     velcro
    0.55
    誂
    0.54
    0.53
    当該
    0.52
    POSITIVE LOGITS
     Qin
    0.99
     Xiao
    0.98
     Xia
    0.98
     Xue
    0.94
     Zhao
    0.93
     Yuan
    0.92
     Jiang
    0.91
     Zhang
    0.90
     Tian
    0.89
     Xu
    0.88
    Activations Density 0.139%

    No Known Activations