© 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. 59460
    Prev
    Next
    INDEX
    Explanations

    comparable programming interfaces

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

    This neuron activates on occurrences of the comparison interface or method names “Comparable” and “compareTo.”

    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
     -
    -2.50
    готовки
    -1.92
    si
    -1.88
    鲼
    -1.74
     imma
    -1.70
     mittlere
    -1.69
    HandlerContext
    -1.66
    ↵
    -1.66
    AntiForgeryToken
    -1.64
     ‘
    -1.59
    POSITIVE LOGITS
     of
    1.84
    Somebody
    1.84
     으로
    1.81
    ～。
    1.77
    年
    1.68
    英語版
    1.66
    するという
    1.66
     belangrij
    1.63
    नलोड
    1.61
    馐
    1.60
    Activations Density 0.001%

    No Known Activations