© 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. 3487
    Prev
    Next
    INDEX
    Explanations

    The neuron is activating on content words—especially multi‐syllabic nouns and adjectives—rather than on function words.

    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
     এবং
    1.98
     และ
    1.93
     and
    1.87
     và
    1.86
     आणि
    1.82
     और
    1.80
     અને
    1.77
    และ
    1.74
     и
    1.73
     και
    1.73
    POSITIVE LOGITS
     accordingly
    1.09
     Consequently
    0.97
     therefrom
    0.96
     thereafter
    0.96
     Accordingly
    0.96
     therewith
    0.94
     Subsequently
    0.88
     Therefore
    0.86
     উভয়
    0.86
     pertanto
    0.83
    Activations Density 0.364%

    No Known Activations