© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10042
    Prev
    Next
    INDEX
    Explanations

    font style and color

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

    The neuron strongly activates on structured, procedural or instructional text—especially formatted guidelines, technical steps, or manual‐style passages.

    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
    启用
    0.57
     clearfix
    0.55
    casus
    0.55
     vetted
    0.54
     BorderLayout
    0.54
    箱
    0.54
     избира
    0.53
    াহিনী
    0.53
    BackgroundImage
    0.52
     named
    0.51
    POSITIVE LOGITS
     fontWeight
    1.18
    字体
    1.17
    fontWeight
    1.16
    font
    1.10
     font
    1.09
    文字
    1.09
    字
    1.09
     bold
    1.05
    FONT
    1.05
    setFont
    1.04
    Activations Density 0.059%

    No Known Activations