© 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. 15482
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to color names (e.g. “Blue”).

    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
     выполнять
    0.88
     строка
    0.85
     брать
    0.83
     периоди
    0.83
     подключа
    0.79
     padrões
    0.79
    Ⅼ
    0.78
     выполняется
    0.77
     núcle
    0.76
    expandedTitle
    0.75
    POSITIVE LOGITS
    м
    0.86
    म
    0.82
    ي
    0.77
    م
    0.76
    !
    0.75
    ↵
    0.75
    <0x80>
    0.75
    '
    0.75
    (
    0.71
    سب
    0.70
    Activations Density 0.000%

    No Known Activations