© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15742
    Prev
    Next
    INDEX
    Explanations

    using or moving Earth, or explaining methods

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron selectively activates on decimal‐formatted numbers (i.e. tokens containing a period and digits).

    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
    ไม่มี
    0.88
    ę
    0.86
    มา
    0.79
    เพ
    0.79
    нг
    0.78
    인
    0.77
    를
    0.77
     وإ
    0.77
     لا
    0.75
    개
    0.75
    POSITIVE LOGITS
     argon
    0.98
     revitalize
    0.92
     Gazprom
    0.88
     cifras
    0.88
     Lola
    0.87
     gratifying
    0.87
     demean
    0.84
     queer
    0.81
     exuber
    0.81
     muster
    0.80
    Activations Density 0.001%

    No Known Activations