© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1769
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on named entities and numeric tokens—e.g. people’s names, organizations, places, and numbers.

    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
    it
    0.92
    ar
    0.92
    ely
    0.87
    š
    0.86
    in
    0.85
    el
    0.80
    on
    0.80
    >"
    0.79
    contained
    0.79
    as
    0.78
    POSITIVE LOGITS
    лина
    0.83
    тная
    0.82
     Vér
    0.81
    ковая
    0.80
    кина
    0.77
    ى
    0.77
    личи
    0.76
     AppMethodBeat
    0.75
     Бере
    0.75
    роятно
    0.74
    Activations Density 0.654%

    No Known Activations