© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5343
    Prev
    Next
    INDEX
    Explanations

    disease at

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

    The neuron detects formal website disclaimer or legal‐responsibility language (liability, “at your own risk,” correctness of information, free-of-charge terms).

    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_31_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
    지난
    0.53
    裡面
    0.52
    વામાં
    0.52
     நாட்களில்
    0.51
    ผ่านมา
    0.50
    晒
    0.48
    eszcze
    0.48
     течение
    0.48
     තුළ
    0.48
     बगल
    0.47
    POSITIVE LOGITS
     at
    3.77
     atthe
    2.95
     tại
    2.48
    于
    2.33
    於
    2.27
     于
    2.14
     ở
    2.02
     At
    1.93
    atthe
    1.91
     Tại
    1.91
    Activations Density 1.400%

    No Known Activations