© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19922
    Prev
    Next
    INDEX
    Explanations

    jd and Magento

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

    The neuron fires on vendor or project identifiers—e.g. tokens like “Magento” or “jd.”

    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
     It
    -2.97
     būtų
    -2.66
    งิน
    -2.42
    蛰
    -2.36
     This
    -2.30
     Their
    -2.25
     Pokud
    -2.25
     arcane
    -2.23
     unholy
    -2.20
     afectan
    -2.19
    POSITIVE LOGITS
    薆
    2.58
     they
    2.55
     oleh
    2.55
    *
    2.34
     linge
    2.34
     短发
    2.33
    甞
    2.33
    のは
    2.27
    掼
    2.22
    酹
    2.20
    Activations Density 0.003%

    No Known Activations