© 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. 11065
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on terms related to risk, protection, and well-being—especially around safety, health, security, and privacy.

    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
    ATE
    0.77
     создание
    0.76
     getDate
    0.75
    寐
    0.71
     जी
    0.70
    CE
    0.69
     छोर
    0.69
     만든
    0.68
     sunroof
    0.68
    Volatility
    0.68
    POSITIVE LOGITS
    يا
    0.92
    措施
    0.79
    មា
    0.75
     issues
    0.73
    Richt
    0.73
    т
    0.73
     Bila
    0.71
     tę
    0.70
     заход
    0.70
    জন
    0.70
    Activations Density 0.277%

    No Known Activations