© 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. 11760
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on the very first content word (or headline token) at the start of a new text block or paragraph.

    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
     sorprendente
    0.84
    长安
    0.83
    损伤
    0.82
     sial
    0.80
    大约
    0.80
    ဵ
    0.79
    较为
    0.79
     kurang
    0.78
    可在
    0.78
    ற்கு
    0.78
    POSITIVE LOGITS
    I
    0.94
    П
    0.91
    ни
    0.83
    AA
    0.78
    A
    0.77
    な
    0.73
    Б
    0.70
    ?
    0.69
    Đ
    0.68
    О
    0.67
    Activations Density 0.000%

    No Known Activations