© 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. 34-GEMMASCOPE-RES-131K
    7. 63504
    Prev
    Next
    INDEX
    Explanations

    rhizomes, tubers, bulbs, roots

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

    This neuron identifies plant anatomical structures, particularly rhizomes, tubers, and other underground plant organs.

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

    The neuron strongly responds to technical botanical and biological nomenclature, especially Latin genus/species names and specialized plant‐part terms (e.g. rhizome, Curcuma, Rheum palmatum).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    UserScript
    -0.74
     вак
    -0.70
    шев
    -0.69
     dầu
    -0.69
    灌
    -0.68
     درخت
    -0.67
     perca
    -0.67
    ené
    -0.66
    THREAD
    -0.66
    TREE
    -0.66
    POSITIVE LOGITS
     rhiz
    2.61
     tubers
    2.45
     bulbs
    2.13
     tuber
    2.05
     underground
    1.90
     bulb
    1.74
     Rhiz
    1.74
     Bulbs
    1.73
    tuber
    1.58
    underground
    1.57
    Activations Density 0.083%

    No Known Activations