© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10358
    Prev
    Next
    INDEX
    Explanations

    libraries and archives

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

    The neuron activates on mentions of libraries and related terms (e.g., library, librarian, library services).

    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
     कंपनियों
    0.61
    医疗
    0.61
    蟶
    0.60
     Brands
    0.60
    产能
    0.60
    Brands
    0.59
     diarrh
    0.59
     चिकन
    0.59
    鯽
    0.59
     scams
    0.58
    POSITIVE LOGITS
     library
    2.72
     библиоте
    2.70
     biblioteca
    2.67
     librarians
    2.64
     бібліоте
    2.63
     librarian
    2.61
     библиотека
    2.59
     libraries
    2.56
     bibli
    2.52
     Library
    2.50
    Activations Density 0.500%

    No Known Activations