© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130790
    Prev
    Next
    INDEX
    Explanations

    Magento sales and catalog code

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

    The neuron fires on code identifiers and module/class/resource names (e.g. Magento/Drupal API paths, class names, and other programming‐related tokens).

    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
    esercito
    -1.42
    itize
    -1.32
     kön
    -1.26
    ೬
    -1.25
    hecta
    -1.20
    🫶
    -1.20
     ór
    -1.19
    ζει
    -1.18
     could
    -1.17
    
    -1.17
    POSITIVE LOGITS
     suoi
    1.48
     общий
    1.48
     dispuesto
    1.46
     beinhaltet
    1.46
    ONLY
    1.39
    </strong>
    1.39
     verbreitet
    1.37
    دیگر
    1.28
     возникает
    1.27
     luoghi
    1.25
    Activations Density 0.121%

    No Known Activations