© 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. 13995
    Prev
    Next
    INDEX
    Explanations

    context

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

    The neuron fires on longer, multi-syllabic content words—especially abstract nouns (e.g. “conjecture,” “consensus,” “legacy,” “heritage,” “lineage,” “longevity,” “context(ually)”).

    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
    egin
    0.66
    ivation
    0.66
    ંદર
    0.63
    焜
    0.63
    ιώ
    0.61
    zit
    0.59
    teilung
    0.57
    inoa
    0.57
    शय
    0.56
    usura
    0.56
    POSITIVE LOGITS
     driven
    0.84
     மிக்க
    0.80
    driven
    0.79
     nél
    0.77
    শালী
    0.71
     razones
    0.70
    ાઇ
    0.68
    -
    0.67
    ভুক্ত
    0.66
    ized
    0.66
    Activations Density 0.554%

    No Known Activations