© 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. 14793
    Prev
    Next
    INDEX
    Explanations

    proprioception and propionic acid

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

    This neuron detects scientific terminology related to biochemical compounds, especially words ending in "onic", "ception", and "ate" like "proprioception" and "propionate".

    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
    ar
    -3.22
    or
    -2.86
    S
    -2.84
     This
    -2.73
     неболь
    -2.67
    2
    -2.67
    )
    -2.47
    B
    -2.47
    </h1>
    -2.41
     The
    -2.41
    POSITIVE LOGITS
     ハロウィン
    2.92
     水墨
    2.80
     間取り
    2.78
     Organizador
    2.78
    
    2.77
     放題
    2.73
     菇
    2.72
    ⢌
    2.67
     policia
    2.67
     ヶ
    2.63
    Activations Density 0.003%

    No Known Activations