© 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. 9699
    Prev
    Next
    INDEX
    Explanations

    Santa Cruz

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

    The neuron strongly activates on structured species‐factsheet metadata and citation headers—e.g. “Species factsheet,” scientific names, download URLs, dates, and recommended citation lines.

    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
     envej
    0.59
    ྂ
    0.57
     নির্যা
    0.57
     annuity
    0.56
    imitives
    0.55
     स्वातंत्र्य
    0.55
    スク
    0.55
    争
    0.54
     連
    0.54
     ristrutt
    0.54
    POSITIVE LOGITS
     Taxonomic
    1.88
     taxonomic
    1.86
     Biodiversity
    1.52
     taxon
    1.51
     Zoological
    1.49
     Wildlife
    1.44
     biologists
    1.41
     IUCN
    1.41
     Zoology
    1.41
     Fauna
    1.40
    Activations Density 0.359%

    No Known Activations