© 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. 8478
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on general‐purpose nouns referring to entities or roles (e.g. “agent,” “machines,” “average”).

    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
     esperamos
    0.88
    myButtons
    0.83
     Enseñ
    0.82
     Temperaturen
    0.77
     mensagens
    0.77
     Algebras
    0.76
    )]^{
    0.76
     Союза
    0.74
     polskich
    0.74
     Chỉ
    0.74
    POSITIVE LOGITS
    nelle
    0.78
    rds
    0.75
    tex
    0.73
    s
    0.71
    m
    0.71
    y
    0.71
    tegr
    0.70
    lr
    0.70
    it
    0.70
    l
    0.70
    Activations Density 0.000%

    No Known Activations