© 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. 24-GEMMASCOPE-2-RES-16K
    7. 10210
    Prev
    Next
    INDEX
    Explanations

    to entertaining or unusual

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

    This neuron strongly activates on standalone capitalized tokens—proper names, acronyms, or other named‐entity labels.

    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_24_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
    西安
    0.74
    。
    0.74
    ทะเบียน
    0.71
    Abbreviations
    0.70
    Š
    0.70
     الوطنية
    0.68
    _
    0.68
    相应的
    0.67
    Auto
    0.66
    ByIndex
    0.66
    POSITIVE LOGITS
    mless
    0.86
    spirited
    0.84
     ਦਿ
    0.79
     vinden
    0.78
     anni
    0.78
    નના
    0.78
     bhikkhave
    0.77
    𝗹
    0.77
     pense
    0.76
    mie
    0.76
    Activations Density 0.001%

    No Known Activations