© 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. 3332
    Prev
    Next
    INDEX
    Explanations

    Indonesia

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

    The neuron flags the start of the main article body—long contiguous prose paragraphs—distinguishing them from headings, dates, or other meta‐data.

    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
    áme
    0.83
     ná
    0.83
     Kör
    0.80
     Lö
    0.80
     Ú
    0.78
    áv
    0.77
    vě
    0.77
    í
    0.77
     Leigh
    0.76
     Flüss
    0.76
    POSITIVE LOGITS
    Indonesia
    2.14
     masyarakat
    2.03
     Indonesian
    1.96
     Indonesia
    1.93
     kemudian
    1.89
     melakukan
    1.84
     menjadi
    1.84
     memiliki
    1.82
     hingga
    1.81
     kegiatan
    1.81
    Activations Density 0.565%

    No Known Activations