© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5603
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens—especially decimal‐formatted 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_24_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
    createNew
    0.70
    在
    0.70
    nr
    0.66
     және
    0.64
     أن
    0.64
     এবং
    0.62
    setUp
    0.62
     প্রমুখ
    0.61
     इन
    0.60
     и
    0.59
    POSITIVE LOGITS
     comida
    0.77
     others
    0.76
     fiance
    0.73
     Educação
    0.70
     Others
    0.69
     memorabilia
    0.68
     Justiça
    0.68
     perdón
    0.65
     financials
    0.63
     forgiveness
    0.62
    Activations Density 0.919%

    No Known Activations