© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69715
    Prev
    Next
    INDEX
    Explanations

    plant scientific names ending in L

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

    The neuron identifies scientific Latin species names followed by "L." (Linnaeus) in botanical and biological literature.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron flags occurrences of Latin binomial species names (especially those ending in “L.”) in bibliographic citations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    糁
    -1.50
    鵙
    -1.50
    ul
    -1.46
     nonchal
    -1.45
    蜮
    -1.42
    苼
    -1.41
     formid
    -1.40
    踯
    -1.38
     magnific
    -1.38
    enie
    -1.37
    POSITIVE LOGITS
     makes
    1.71
     time
    1.62
     could
    1.52
     When
    1.48
     increase
    1.42
     make
    1.29
     seemed
    1.28
    !!!!
    1.28
     avoid
    1.28
     increased
    1.28
    Activations Density 0.029%

    No Known Activations