© 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. 24-GEMMASCOPE-2-RES-16K
    7. 10362
    Prev
    Next
    INDEX
    Explanations

    project leads

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

    The neuron strongly responds to UI‐style action words that prompt users to choose or refine options (e.g. “Make,” “Filter”), effectively spotting interface command verbs.

    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_24_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
     legumes
    0.90
    ística
    0.85
    ພວກເຮ
    0.85
    РИ
    0.84
     준비
    0.84
    点で
    0.83
    チャン
    0.81
    准备
    0.79
    蛎
    0.79
     타이
    0.79
    POSITIVE LOGITS
    า
    0.80
    א
    0.76
    ا
    0.75
     सच्चे
    0.72
    ุน
    0.69
     рус
    0.68
     event
    0.67
     naturally
    0.66
    \%
    0.64
     mathemat
    0.64
    Activations Density 0.000%

    No Known Activations