© 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. 5725
    Prev
    Next
    INDEX
    Explanations

    phone numbers with hyphens and parentheses

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

    The neuron fires on pieces of web addresses (e.g. “http://”, domain name fragments, “.com”, etc.), i.e. substrings of URLs.

    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
    🔪
    0.70
     loopt
    0.68
     anteriores
    0.68
    ²/
    0.68
     élev
    0.68
     điển
    0.66
     independientes
    0.66
     indépend
    0.65
     sehr
    0.64
     spezi
    0.63
    POSITIVE LOGITS
    zh
    0.59
    wp
    0.59
    zq
    0.57
    yana
    0.57
    ぐる
    0.57
    河南省
    0.57
    lomer
    0.56
    僻
    0.56
    xing
    0.55
    dus
    0.54
    Activations Density 0.041%

    No Known Activations