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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9775
    Prev
    Next
    INDEX
    Explanations

    fizzBuzz pattern detection

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

    The neuron fires on “metadata”‐style tokens—those that are names, abbreviations, or numbers (i.e. tokens with uppercase letters or 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
    ும்ப
    0.79
     ارب
    0.77
    eben
    0.75
    includegraphics
    0.75
    ли
    0.73
    lima
    0.70
    ި
    0.70
    etu
    0.70
     langt
    0.70
    шие
    0.69
    POSITIVE LOGITS
     menyimpan
    0.75
    করে
    0.74
     banging
    0.74
     fizemos
    0.73
    娀
    0.73
     convers
    0.72
    gloss
    0.72
    Πα
    0.71
    Тер
    0.70
     cambiamenti
    0.70
    Activations Density 0.001%

    No Known Activations