© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4950
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on uncommon or “outlier” tokens—words or symbols that stand out as rare or unexpected in the text.

    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
    вая
    0.86
    CCOCC
    0.79
    ات
    0.77
    ა
    0.76
    ように
    0.75
    aufen
    0.75
    ний
    0.75
     pequenas
    0.75
    ین
    0.74
    _
    0.74
    POSITIVE LOGITS
    דע
    0.83
     odst
    0.72
    rabbit
    0.71
     harvests
    0.71
    )=(
    0.69
     Уже
    0.68
    絟
    0.68
     finan
    0.67
     lessee
    0.67
     Taxation
    0.66
    Activations Density 0.000%

    No Known Activations