© 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. 6623
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens—i.e. digits or numbers (quantities, statistics, counts).

    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
     Obrig
    0.64
    ‎
    0.61
    
    0.59
    
    0.58
     vah
    0.57
    эле
    0.57
    wis
    0.57
     bege
    0.55
     obrig
    0.54
     spotted
    0.54
    POSITIVE LOGITS
     তৃতীয়
    0.87
    第三
    0.80
     তৃতীয়
    0.79
     तीसरा
    0.77
    両
    0.77
    どちら
    0.73
     तीसरे
    0.72
     üçüncü
    0.72
     third
    0.71
    Third
    0.71
    Activations Density 0.108%

    No Known Activations