© 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. 10444
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens (especially floating‐point or decimal 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
     mieszkań
    0.81
     ks
    0.72
     ثاني
    0.72
     zdję
    0.70
     rád
    0.68
     Grac
    0.68
     Ř
    0.66
     Ano
    0.66
     zakład
    0.66
     thay
    0.65
    POSITIVE LOGITS
    ל
    0.89
    Boolean
    0.80
    യ
    0.80
    رس
    0.77
    ಪ
    0.77
    伤害
    0.76
    Species
    0.74
    ยาน
    0.73
    לט
    0.73
    Sev
    0.72
    Activations Density 0.000%

    No Known Activations