© 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. 67574
    Prev
    Next
    INDEX
    Explanations

    barley grain

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

    scientific names of plants, including botanical terms and crop species.

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

    The neuron detects Latin scientific taxonomic names (especially plant genus and species epithets) in the 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
    </h2>
    -1.87
    ")){
    -1.48
    %")
    -1.42
    ")}
    -1.41
     gewel
    -1.41
     about
    -1.38
     ③
    -1.36
    ")));
    -1.35
     Erden
    -1.35
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.34
    POSITIVE LOGITS
     I
    1.72
    Meskipun
    1.52
    Secara
    1.41
     lukewarm
    1.34
     drawbacks
    1.32
    Více
    1.30
     Matériau
    1.23
    5
    1.23
    Inhalte
    1.23
     πάντα
    1.22
    Activations Density 0.117%

    No Known Activations