© 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. 10127
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on scientific and taxonomic terminology—Latin genus/species names, family names, and specialized biological or biochemical terms.

    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
     виртуа
    0.65
     стандарт
    0.60
     ㅛ
    0.60
    社區
    0.58
    azał
    0.57
    ційний
    0.57
     USDT
    0.57
     siyah
    0.56
    뿡
    0.56
     Jungkook
    0.55
    POSITIVE LOGITS
     subfamily
    1.37
     superfamily
    1.25
     family
    1.21
     семейства
    1.09
     class
    1.08
     familia
    1.06
     subclass
    1.05
    family
    1.05
     subgroup
    1.03
     category
    1.01
    Activations Density 0.317%

    No Known Activations