© 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. 12246
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect numeric tokens (numbers and numeric values) 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
     অস্বীকার
    0.52
    Variance
    0.51
     জিনিস
    0.50
     (;
    0.50
    variance
    0.50
    質感
    0.49
    ピソード
    0.49
    谆
    0.49
     PyQt
    0.49
    緑
    0.49
    POSITIVE LOGITS
    হাত
    0.66
     nitrog
    0.63
    nit
    0.59
    Lambda
    0.59
    netlify
    0.58
    Nit
    0.57
     Lambda
    0.56
     nitrate
    0.55
     koa
    0.55
    ambda
    0.54
    Activations Density 0.010%

    No Known Activations