© 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. 224
    Prev
    Next
    INDEX
    Explanations

    write code

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

    This neuron detects structural or metadata tokens—things like code‐include directives with angle brackets, dates and times, version or author labels, and other header/markup elements.

    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
     nég
    0.37
    seated
    0.36
    Gone
    0.36
    ின்றனர்
    0.36
    goers
    0.35
    mailed
    0.35
    Clicked
    0.35
     fairs
    0.35
     الزد
    0.35
     denkt
    0.34
    POSITIVE LOGITS
    ชื่อ
    0.38
    leetcode
    0.37
     게임
    0.37
     Văn
    0.36
    小米
    0.36
     エ
    0.35
    京东
    0.35
     PostgreSQL
    0.34
     TensorFlow
    0.34
     Proyecto
    0.34
    Activations Density 0.162%

    No Known Activations