© 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. 77367
    Prev
    Next
    INDEX
    Explanations

    Java package declarations

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

    The neuron fires on Java package and fully‐qualified class path tokens (e.g. “package com.example.foo” or similar Java namespace declarations).

    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
    下面
    -0.78
     constraints
    -0.77
     куртка
    -0.73
     móg
    -0.73
     should
    -0.73
     tanpa
    -0.72
    seud
    -0.72
     without
    -0.71
     affected
    -0.71
     indicadores
    -0.71
    POSITIVE LOGITS
     Arrays
    1.49
     arrays
    1.27
    Arrays
    1.24
     OOP
    1.14
     loops
    1.07
     Collections
    1.07
     Inheritance
    1.02
    day
    0.96
    arrays
    0.95
    noinspection
    0.94
    Activations Density 0.048%

    No Known Activations