© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4036
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on words and short phrases that introduce or signal an explanation or causal reason in the text.

    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
     hvilket
    0.71
    どれ
    0.68
     jakiś
    0.68
     який
    0.67
     Какой
    0.64
     który
    0.64
    ๕
    0.64
     кто
    0.62
    愛的
    0.61
     effectually
    0.61
    POSITIVE LOGITS
     mengapa
    1.02
     why
    0.96
    为什么
    0.93
     kenapa
    0.92
     이유
    0.91
     Почему
    0.87
    why
    0.86
    Почему
    0.86
    왜
    0.85
    なぜ
    0.83
    Activations Density 0.337%

    No Known Activations