© 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. 4334
    Prev
    Next
    INDEX
    Explanations

    meditation scan reduction learning

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

    The neuron strongly activates on capitalized proper nouns—names of people, places, organizations, and other named entities.

    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
    邵
    0.52
    getSaveLocation
    0.51
    orschungs
    0.49
    َ
    0.47
    ufficient
    0.47
    лефон
    0.47
    接下来
    0.46
    各位同學
    0.46
    ﻌ
    0.45
    ستخدم
    0.45
    POSITIVE LOGITS
     of
    0.85
     ofthe
    0.81
    in
    0.78
    sof
    0.62
    os
    0.61
    on
    0.61
    es
    0.61
     Of
    0.61
    men
    0.60
     this
    0.59
    Activations Density 1.624%

    No Known Activations