© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45400
    Prev
    Next
    INDEX
    Explanations

    order related actions

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

    This neuron fires on programming-style terms and identifiers (e.g. Magento event names, method/class names, snake_case tokens) 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_34/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
     ката
    -0.81
     overflow
    -0.74
     ataque
    -0.71
     tric
    -0.70
     básicos
    -0.69
     записа
    -0.69
     конди
    -0.67
    iras
    -0.66
    Publish
    -0.66
     deviations
    -0.66
    POSITIVE LOGITS
     order
    0.91
    Комментарий
    0.83
    Sca
    0.83
    备注
    0.80
     Baxter
    0.77
    感的
    0.77
     guest
    0.77
     Invoice
    0.76
    Nissan
    0.75
    Thief
    0.75
    Activations Density 0.025%

    No Known Activations