© 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. 5307
    Prev
    Next
    INDEX
    Explanations

    "The" followed by a noun

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

    The neuron spotlights the very first word of sentences or major clauses.

    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_31_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
    (?)
    1.10
     (?)
    0.91
    (!)
    0.86
    둰
    0.73
    ..(
    0.69
    (?
    0.66
     (!)
    0.64
    눙
    0.64
    ূর্ন
    0.62
    //////
    0.59
    POSITIVE LOGITS
     They
    0.93
     …
    0.84
     The
    0.84
     آن‌ها
    0.84
     wikiHow
    0.82
     Daarom
    0.80
     Then
    0.77
     These
    0.77
     її
    0.77
    ߋ
    0.75
    Activations Density 1.485%

    No Known Activations