© 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. 14588
    Prev
    Next
    INDEX
    Explanations

    from [concept] to

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

    The neuron preferentially activates on long, multisyllabic or uncommon subword tokens (e.g. technical vocabulary or lengthy terms).

    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
     사람들
    0.64
    但在
    0.60
     법칙
    0.59
     Nhưng
    0.56
     사람들이
    0.56
     자체가
    0.54
    quée
    0.54
    ிகளும்
    0.53
     같은
    0.53
    abhavo
    0.53
    POSITIVE LOGITS
     الى
    1.12
     to
    1.07
     إلى
    1.05
     into
    0.91
    到
    0.91
     onward
    0.79
    へと
    0.75
    into
    0.75
    to
    0.73
    にかけて
    0.70
    Activations Density 0.071%

    No Known Activations