© 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. 6284
    Prev
    Next
    INDEX
    Explanations

    The neuron almost exclusively activates on numeric tokens, i.e. sequences of digits or 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
    c
    0.79
    j
    0.79
    i
    0.76
    sys
    0.75
    sn
    0.75
    jq
    0.73
     Aralık
    0.71
     }_{\
    0.70
    pq
    0.70
     ©️
    0.70
    POSITIVE LOGITS
    лы
    0.80
    ร่างกาย
    0.80
    自分で
    0.77
    нг
    0.76
    釘
    0.75
     equil
    0.74
    ough
    0.74
     bodily
    0.73
     कोई
    0.73
     کوئی
    0.73
    Activations Density 0.000%

    No Known Activations