© 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. 3972
    Prev
    Next
    INDEX
    Explanations

    The neuron chiefly fires on numeric literal tokens—especially decimal numbers and other measured values.

    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
    QU
    0.73
    Rw
    0.73
    
    0.73
     consenso
    0.67
    ﹚
    0.67
    珀
    0.66
    岗位
    0.65
    RAMM
    0.65
    JO
    0.65
    Rv
    0.65
    POSITIVE LOGITS
    álně
    0.92
    sl
    0.79
     Фі
    0.79
    ----------------
    0.79
     일
    0.77
    лы
    0.73
     드
    0.73
     Фи
    0.72
    retour
    0.72
     plaats
    0.72
    Activations Density 0.001%

    No Known Activations