© 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. 11788
    Prev
    Next
    INDEX
    Explanations

    tip-related words

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

    The neuron strongly activates on section‐style headings or labels followed by a colon (e.g. “Tip:” or “Microsoft Visual Studio Tips:”).

    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
     झाल
    0.61
    켰
    0.59
    老公
    0.58
    꿨
    0.55
    獬
    0.54
     मामला
    0.54
     স্বামী
    0.53
    quad
    0.52
    戏
    0.51
     자동차
    0.50
    POSITIVE LOGITS
    ៌
    0.66
    ).[
    0.56
    
    0.55
     Fuss
    0.54
     mús
    0.54
     ateliers
    0.53
    ₜ
    0.53
     बलों
    0.52
     casks
    0.52
    樊
    0.52
    Activations Density 0.000%

    No Known Activations