© 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. 5543
    Prev
    Next
    INDEX
    Explanations

    both countries

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects numeric tokens—especially counts, statistics, and other 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_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
    मुख
    0.69
    贈り
    0.68
    こうした
    0.66
    他にも
    0.65
    แม
    0.64
    従業
    0.64
    簷
    0.63
     affection
    0.62
     adatt
    0.62
    覧
    0.62
    POSITIVE LOGITS
     вычисли
    0.82
    htt
    0.73
    ration
    0.70
     Наи
    0.70
     девушки
    0.70
    ý
    0.69
     табле
    0.66
    ched
    0.66
     Tb
    0.66
    grams
    0.65
    Activations Density 0.000%

    No Known Activations