© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15550
    Prev
    Next
    INDEX
    Explanations

    The neuron is a specialist for the coordinating conjunction “and,” particularly when it links or adds elements in a list or paired clauses.

    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
    Ꮷ
    0.93
    쐞
    0.84
    нче
    0.83
    นี
    0.81
    ncia
    0.81
    Hybrid
    0.80
    Excelente
    0.79
    졔
    0.79
    Were
    0.79
     Siles
    0.79
    POSITIVE LOGITS
    amment
    0.73
     እና
    0.67
    PRESSED
    0.67
     folders
    0.65
    toEqual
    0.65
    efined
    0.64
     woning
    0.64
     두고
    0.63
    ﺱ
    0.62
     ファイル
    0.62
    Activations Density 0.001%

    No Known Activations