© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5832
    Prev
    Next
    INDEX
    Explanations

    information and system attributes

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

    The neuron fires on technical “example/embodiment” headings or labels (e.g. “实施例 4,” “Example 1,” “実施例4”).

    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
    は見
    0.86
    はありません
    0.79
    もあります
    0.73
    などは
    0.73
    等は
    0.72
    もあり
    0.71
    理由は
    0.69
    はお
    0.68
    までは
    0.64
    though
    0.64
    POSITIVE LOGITS
    における
    1.15
    的一种
    1.13
     všech
    1.02
    的一个
    1.01
    的一部分
    1.00
    的一個
    1.00
     svih
    1.00
    ைகளின்
    0.98
    中的
    0.93
    에서의
    0.93
    Activations Density 0.022%

    No Known Activations