© 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. 22-GEMMASCOPE-RES-131K
    4. 79615
    Prev
    Next
    INDEX
    Explanations

    java stream operations

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

    This neuron detects references to Java’s Stream API—especially mentions of “stream” (and related Java 8 stream usage).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     lascia
    -1.22
     estadia
    -1.11
     特典
    -1.09
    lichten
    -1.04
     Serviço
    -1.02
     schnee
    -0.99
     Espanha
    -0.98
    ittäin
    -0.98
     riesce
    -0.97
     garantis
    -0.97
    POSITIVE LOGITS
    党的
    1.09
     It
    1.05
      
    1.02
    man
    1.02
    佼
    1.01
     from
    0.99
    nick
    0.99
    鳄
    0.97
    ⫺
    0.96
    oo
    0.96
    Activations Density 0.004%

    No Known Activations