© 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. 8300
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on blank or whitespace-only lines, effectively detecting paragraph or line breaks.

    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
     さん
    0.78
     这个
    0.77
     我
    0.73
     THAT
    0.73
     這個
    0.71
     ख़
    0.67
     congrats
    0.67
     Congrats
    0.67
     SUCH
    0.66
    你好
    0.66
    POSITIVE LOGITS
    <u>
    0.53
     quasi
    0.48
     prism
    0.47
    きの
    0.47
     주어진
    0.46
    ため
    0.44
    ادرة
    0.43
     lucr
    0.43
     سبيل
    0.43
    लिये
    0.41
    Activations Density 0.004%

    No Known Activations