© 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. 7711
    Prev
    Next
    INDEX
    Explanations

    The neuron is firing only on tokens with very high internal token‐ID numbers (i.e. rare or high-indexed vocabulary items) rather than any ordinary word.

    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
     p
    0.62
     возраста
    0.59
    :
    0.59
    )
    0.58
    )?.
    0.55
    p
    0.54
    ,
    0.53
     IP
    0.53
     ск
    0.53
     проведе
    0.53
    POSITIVE LOGITS
    ōng
    0.76
    valment
    0.76
    vous
    0.74
     では
    0.73
     Thì
    0.71
     विंड
    0.71
    peł
    0.71
    Gọi
    0.71
    ustainability
    0.71
    ouest
    0.70
    Activations Density 0.002%

    No Known Activations