© 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. 7957
    Prev
    Next
    INDEX
    Explanations

    plant names and their parts

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

    This neuron identifies plant and botanical names, particularly focusing on various plant species, fruits, herbs, and natural substances.

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

    This neuron activates on botanical names (plant species or genera, often in their Latin scientific form).

    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
     bensin
    -1.64
    滟
    -1.59
    tional
    -1.56
     naam
    -1.56
     Cette
    -1.55
     ſec
    -1.52
     AUTHORITIES
    -1.44
     ſp
    -1.44
     iyo
    -1.43
    juries
    -1.42
    POSITIVE LOGITS
     emphasized
    1.64
    )
    1.63
    寕
    1.63
     that
    1.61
     姉
    1.51
     for
    1.48
     may
    1.47
     resulted
    1.45
     brought
    1.45
     neatly
    1.45
    Activations Density 0.027%

    No Known Activations