© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58837
    Prev
    Next
    INDEX
    Explanations

    plant and associated descriptors

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

    references to plants or plant-related terms in scientific or technical texts.

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

    The neuron strongly activates on mentions of the plant organism (and its direct morphological forms) in scientific text.

    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
    s
    -2.08
    彻底
    -1.92
    ↵
    -1.82
    她是
    -1.80
    ed
    -1.74
     saveurs
    -1.74
     
    -1.67
    住在
    -1.66
    '~
    -1.64
    尤其
    -1.62
    POSITIVE LOGITS
    </h3>
    2.41
     erzählen
    2.38
     Kollegen
    2.33
     pokud
    2.28
     erklär
    2.14
     maravillosas
    2.14
     Krankenhaus
    2.08
     если
    2.08
    內的
    2.08
     gesund
    2.05
    Activations Density 0.027%

    No Known Activations