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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13405
    Prev
    Next
    INDEX
    Explanations

    distractors (incorrect options)

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

    The neuron detects severability language in legal text—phrases stating that if one provision is invalid or unenforceable, the remaining provisions will continue in full force and effect.

    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
     सुद्धा
    0.81
    ᆺ
    0.75
     ਸਾ
    0.70
    otive
    0.70
     д
    0.69
     Цент
    0.69
    UpperBound
    0.67
    니다
    0.66
    antiation
    0.66
     그러나
    0.66
    POSITIVE LOGITS
    l
    1.00
    lv
    0.93
    lists
    0.89
    tables
    0.88
    tops
    0.88
    lz
    0.86
    t
    0.85
    lable
    0.83
    tour
    0.82
    tare
    0.80
    Activations Density 0.002%

    No Known Activations