© 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. 59699
    Prev
    Next
    INDEX
    Explanations

    botanical topics and fields

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

    This neuron identifies botanical terminology and plant-related scientific terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    or
    -1.95
    猡
    -1.89
    鬭
    -1.87
     vader
    -1.82
     Of
    -1.79
    滏
    -1.77
    龗
    -1.77
     توسط
    -1.76
     bors
    -1.75
    hidup
    -1.72
    POSITIVE LOGITS
    </strong>
    2.28
     exacting
    2.20
     departments
    2.02
    O
    2.00
     Freunden
    2.00
     Erkennt
    1.99
    𐐪
    1.91
     Schwangerschaft
    1.91
     treasures
    1.88
     Gästen
    1.88
    Activations Density 0.005%

    No Known Activations