© 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. 1445
    Prev
    Next
    INDEX
    Explanations

    The neuron is primarily activated by numeric tokens (digits and number-like strings, especially multi‐digit or decimal 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
    頃
    0.83
     шуда
    0.75
    PLEMENT
    0.71
    νες
    0.70
    umbia
    0.67
    遢
    0.65
    ellikle
    0.64
     ciudad
    0.64
     المؤس
    0.64
    рида
    0.64
    POSITIVE LOGITS
    ів
    0.82
    的形式
    0.79
    𝚜
    0.79
     habis
    0.78
    性は
    0.77
    例えば
    0.76
    אר
    0.75
    的过程中
    0.74
    kan
    0.73
    Ł
    0.73
    Activations Density 0.003%

    No Known Activations