© 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. 11762
    Prev
    Next
    INDEX
    Explanations

    possible types, positions, variations

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

    The neuron detects decimal‐formatted numbers (with a dot) embedded in URL strings.

    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
     consente
    0.96
    са
    0.90
    за
    0.89
     disequ
    0.88
    이나
    0.88
    थान
    0.83
    я
    0.83
    ь
    0.78
    파
    0.77
    ل
    0.77
    POSITIVE LOGITS
     solidaridad
    0.76
    лены
    0.73
     человеку
    0.72
    entity
    0.70
    uoj
    0.70
    arono
    0.69
     niño
    0.68
    igrant
    0.68
    !("{}",
    0.68
     ortak
    0.67
    Activations Density 0.000%

    No Known Activations