© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7826
    Prev
    Next
    INDEX
    Explanations

    research literature retrieval

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

    The neuron is triggered by mentions of academic publication indexes and database names (e.g. Scopus, Web of Science, PubMed, ProQuest).

    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
     createImage
    0.70
     옷
    0.68
     시즌
    0.63
    㓦
    0.58
     homens
    0.57
     Hafen
    0.57
    dicke
    0.57
     roupas
    0.57
    옷
    0.57
     gros
    0.57
    POSITIVE LOGITS
     bibliographic
    1.23
     databases
    1.21
    检索
    1.19
    PubMed
    1.16
     bibli
    1.11
     Databases
    1.10
     Bibli
    1.09
     Pubmed
    1.09
    数据库
    1.07
    Bibli
    1.07
    Activations Density 0.227%

    No Known Activations