© 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. 5366
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on unusually long individual tokens (i.e. words that are much longer than typical 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_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
     پ
    0.73
     diret
    0.71
    둣
    0.68
     особы
    0.67
     boton
    0.67
     פרו
    0.67
     П
    0.66
     pesso
    0.66
     واضح
    0.66
     рассе
    0.66
    POSITIVE LOGITS
    اك
    0.82
     ceremonies
    0.81
    erialize
    0.79
    o
    0.79
    قطه
    0.76
    li
    0.75
    inchi
    0.75
    ا
    0.75
    ıl
    0.73
    ره
    0.73
    Activations Density 0.000%

    No Known Activations