© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1715
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly fires on standalone numeric tokens (especially digits in dates or statistics).

    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_31_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
     stocking
    0.73
     ტი
    0.68
     रंगों
    0.67
     velvety
    0.67
     stocked
    0.67
     Convergence
    0.66
     उन्होंने
    0.66
     해
    0.64
     outfitted
    0.64
     Combining
    0.64
    POSITIVE LOGITS
    un
    0.82
    ทั่วไป
    0.72
    anches
    0.70
    ✘
    0.69
    pero
    0.68
    認為
    0.67
    thed
    0.66
     dont
    0.65
     inade
    0.64
     insufficient
    0.64
    Activations Density 0.000%

    No Known Activations