© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6832
    Prev
    Next
    INDEX
    Explanations

    obligations and consequences

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

    The neuron strongly activates on multi‐syllabic, content‐bearing words (longer “real” words) rather than short function words.

    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_24_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
    יים
    0.79
    אים
    0.77
     résolution
    0.76
     storico
    0.74
     perchè
    0.73
    들
    0.73
     Bạn
    0.73
     nevy
    0.73
     oči
    0.73
    們
    0.73
    POSITIVE LOGITS
    matically
    0.93
    t
    0.91
     объекта
    0.87
    чная
    0.82
     воды
    0.82
    сная
    0.82
    стный
    0.82
    tional
    0.80
    tad
    0.80
    marked
    0.80
    Activations Density 0.000%

    No Known Activations