© 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. 117838
    Prev
    Next
    INDEX
    Explanations

    code C++, python, patents, news

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

    This neuron detects occurrences of “jni” (e.g. references to JNI headers, namespaces, and types).

    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
    жной
    -0.81
    沐
    -0.73
    jesz
    -0.73
    jaj
    -0.71
     inté
    -0.69
    ık
    -0.69
    gut
    -0.67
    🏳
    -0.67
    WithFormat
    -0.67
     نہ
    -0.66
    POSITIVE LOGITS
    的想法
    0.82
    Chore
    0.81
    oflavin
    0.81
     partiellement
    0.79
     tranches
    0.78
     dwell
    0.78
     grud
    0.77
     Chore
    0.77
    liga
    0.77
     attribué
    0.77
    Activations Density 0.001%

    No Known Activations