© 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. 12725
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on standalone numeric tokens (numbers, digits, or numeric sequences) in the text.

    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
     specimen
    0.62
     Sr
    0.59
    কলাপ
    0.59
     specimens
    0.57
    ⌥
    0.55
    अय
    0.55
     Ayuntamiento
    0.53
     mia
    0.53
    ('+
    0.52
    aua
    0.52
    POSITIVE LOGITS
     Segurança
    0.63
    臓
    0.59
    HUD
    0.58
     safer
    0.58
    思う
    0.58
     arguments
    0.57
     Arguments
    0.57
    ériel
    0.56
    理論
    0.56
    targetReference
    0.55
    Activations Density 0.000%

    No Known Activations