© 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. 11936
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens—especially multi‐digit numbers or numeric values (e.g., years, measurements).

    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
    ти
    0.82
    טור
    0.73
    Edges
    0.71
     constituer
    0.71
    बी
    0.71
    ם
    0.70
    பூ
    0.68
    漁
    0.68
    由来
    0.68
    גיע
    0.68
    POSITIVE LOGITS
     Dixit
    0.79
    s
    0.75
    avits
    0.74
     Verme
    0.73
     LEAR
    0.72
     बीएड
    0.72
     ROLE
    0.70
    ribe
    0.69
     PSY
    0.69
    ATING
    0.67
    Activations Density 0.001%

    No Known Activations