© 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. 5436
    Prev
    Next
    INDEX
    Explanations

    words ending in -tion or -ment

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

    The neuron specializes in spotting abstract, policy‐oriented nouns—especially nominalizations of social and political concepts (e.g. professions, education, reimbursement, political empowerment, revolutions).

    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
    Xem
    0.66
     cỏ
    0.65
    ở
    0.64
    ंख
    0.62
    chamber
    0.62
    impul
    0.61
    verifica
    0.60
    atribut
    0.59
    aków
    0.59
    ｗ
    0.59
    POSITIVE LOGITS
     tion
    0.68
     Ally
    0.64
     ments
    0.63
    0.59
    밌
    0.59
    iments
    0.57
     O
    0.57
     “
    0.56
    ently
    0.55
    aneous
    0.55
    Activations Density 0.122%

    No Known Activations