© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1290
    Prev
    Next
    INDEX
    Explanations

    study materials and questions

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

    The neuron fires on boilerplate metadata and reference elements—things like section headings, page numbers, citation labels, and download/file-format links (e.g. “Download as PDF,” “View online,” “Referatas,” “Page 1 of …”).

    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
    洏
    0.69
    pf
    0.68
    м
    0.68
    もう
    0.68
    殆
    0.64
    :
    0.62
    ing
    0.61
    =
    0.61
    ＝
    0.60
    m
    0.58
    POSITIVE LOGITS
     Alzheimer
    0.81
     Leukemia
    0.79
     Ophthalmology
    0.79
     Epidemiology
    0.76
     qPCR
    0.75
     कुलपति
    0.74
     Facultad
    0.72
     Universidade
    0.72
     교수
    0.72
     université
    0.72
    Activations Density 0.004%

    No Known Activations