© 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. 7917
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on decimal numbers (floating‐point numerals).

    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
    邛
    0.79
     attaqu
    0.77
    猖
    0.70
    ا
    0.70
    JACK
    0.69
     attaque
    0.68
    ković
    0.68
     strcpy
    0.67
     中的
    0.67
     nagyobb
    0.66
    POSITIVE LOGITS
     Aloe
    0.90
     vortices
    0.89
    тировать
    0.85
    ،
    0.85
    ти
    0.84
     میشود
    0.83
     fibroblasts
    0.82
    вым
    0.82
    ச
    0.82
    сті
    0.80
    Activations Density 0.000%

    No Known Activations