© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49554
    Prev
    Next
    INDEX
    Explanations

    java lists and lambda expressions

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

    The neuron activates on Java functional‐style method calls—especially stream/Rx pipelines and lambdas—i.e. method names like forEach, collect (groupingBy), subscribe immediately followed by an open parenthesis and/or a “->” lambda.

    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
     can
    -0.93
     would
    -0.92
    readonly
    -0.87
     however
    -0.83
     about
    -0.83
     However
    -0.82
     Mar
    -0.75
     had
    -0.75
    rog
    -0.74
    These
    -0.74
    POSITIVE LOGITS
     this
    1.02
     этой
    0.94
     dieses
    0.93
     fler
    0.92
     consumidores
    0.91
     Comparator
    0.90
     Courier
    0.88
    Ljava
    0.88
     foran
    0.86
    ิ่น
    0.86
    Activations Density 0.004%

    No Known Activations