© 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. 6389
    Prev
    Next
    INDEX
    Explanations

    dividing or send

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

    The neuron consistently fires on the very first word of new sentences or paragraphs.

    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
    на
    0.86
    ן
    0.83
    ی
    0.78
    ทำการ
    0.77
    ان
    0.76
     elucid
    0.75
    a
    0.72
    taining
    0.72
    elar
    0.71
    presentations
    0.71
    POSITIVE LOGITS
    이죠
    0.71
    叽
    0.71
     '#
    0.70
    ijo
    0.70
     যোগ্য
    0.68
    ijl
    0.67
     Ảnh
    0.66
    꽉
    0.66
    zij
    0.66
    <0xBC>
    0.66
    Activations Density 0.000%

    No Known Activations