© 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. 11866
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on isolated uppercase “S” tokens.

    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
     など
    0.68
     问题
    0.64
     செய்தி
    0.63
    阌
    0.61
    टरीना
    0.59
     olması
    0.59
     hinten
    0.59
     ज्वेल
    0.59
     метра
    0.58
    commonByteArray
    0.58
    POSITIVE LOGITS
    BF
    0.63
    (
    0.62
    Map
    0.59
    te
    0.57
    w
    0.55
    W
    0.55
    L
    0.55
    xt
    0.54
    UID
    0.54
    Existing
    0.54
    Activations Density 0.001%

    No Known Activations