© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 3041
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens (e.g. section numbers, monetary amounts, and other digit sequences).

    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
     مقاب
    0.77
     dürfen
    0.74
    😒
    0.69
     النظر
    0.68
    大家都
    0.66
     اکثریت
    0.65
     свиде
    0.64
     нужно
    0.64
     প্রযোজ
    0.64
     дя
    0.63
    POSITIVE LOGITS
    t
    0.91
    namespaces
    0.80
    region
    0.79
    tains
    0.77
    marca
    0.77
     Seeds
    0.76
    ј
    0.75
    ruz
    0.73
     espace
    0.73
     provient
    0.73
    Activations Density 0.001%

    No Known Activations