© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 9193
    Prev
    Next
    INDEX
    Explanations

    The neuron is essentially a “burst” detector that lights up on unusually rare or out-of-distribution tokens (those with very high idf), rather than any specific semantic category.

    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
    osphère
    0.67
     intensities
    0.66
    ів
    0.64
     fréquence
    0.64
    ilites
    0.64
    ಊ
    0.63
     rouges
    0.62
    ATORY
    0.62
    nesses
    0.62
    пта
    0.62
    POSITIVE LOGITS
     Mohamed
    0.68
     Industri
    0.68
     Aaron
    0.64
    สา
    0.64
     Commercial
    0.63
     Ahmed
    0.63
     Ahmad
    0.63
    ara
    0.62
     Saeed
    0.62
     आलो
    0.61
    Activations Density 0.000%

    No Known Activations