© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13769
    Prev
    Next
    INDEX
    Explanations

    This neuron fires strongly on the very first content word of each new section or paragraph, effectively marking paragraph/section beginnings.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    다
    0.73
    िका
    0.72
    있는
    0.71
    Established
    0.67
    鷲
    0.67
    তে
    0.66
    ・・
    0.65
    سی
    0.65
    ѓ
    0.65
    judice
    0.64
    POSITIVE LOGITS
     ellos
    0.82
     ODM
    0.80
     transmutation
    0.77
    ໍ່
    0.71
     ISPs
    0.71
    梩
    0.71
    ুমাত্র
    0.71
     nanot
    0.71
     antagonists
    0.70
     точек
    0.70
    Activations Density 0.000%

    No Known Activations