© 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. 11096
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on content‐bearing nouns (especially proper nouns and key topic words).

    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
     경우는
    0.77
    新的
    0.64
    带动
    0.64
     wobei
    0.63
    加强
    0.63
    =
    0.63
    则
    0.62
    یکه
    0.62
    增加
    0.61
     जोकि
    0.61
    POSITIVE LOGITS
     thậm
    0.88
    !).
    0.86
    
    0.82
     imaginable
    0.78
    ――
    0.76
     gobl
    0.74
    ––
    0.74
     некоторые
    0.73
     മാത്രമല്ല
    0.72
    เหล่านี้
    0.72
    Activations Density 0.122%

    No Known Activations