© 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. 75938
    Prev
    Next
    INDEX
    Explanations

    transaction or technical terms

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

    The neuron strongly activates on code‐style identifiers and markup tags (e.g. function names, class names, HTML/XML element names).

    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
    靶
    -0.81
    OfYear
    -0.78
     тести
    -0.78
    🖲
    -0.75
    fay
    -0.75
    cible
    -0.74
    ographical
    -0.71
     Counties
    -0.71
    ENARIO
    -0.70
     vooraf
    -0.70
    POSITIVE LOGITS
     transaction
    1.09
     transactions
    1.00
     transacciones
    0.88
    力和
    0.85
    getTransaction
    0.84
    transactions
    0.84
     Transaction
    0.82
    essentiel
    0.81
    Legs
    0.80
     legs
    0.79
    Activations Density 0.001%

    No Known Activations