© 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. 103632
    Prev
    Next
    INDEX
    Explanations

    Java JDK versions

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

    The neuron detects software or technical version information, i.e. sequences of numbers, dots, and trademark/product labels that indicate version strings.

    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
    弟弟
    -0.82
    yny
    -0.77
    vrier
    -0.73
     địch
    -0.71
    弩
    -0.70
     المعيار
    -0.69
     conveyance
    -0.69
     verbindet
    -0.69
     karyawan
    -0.68
    fection
    -0.68
    POSITIVE LOGITS
    jdk
    1.03
     Java
    1.02
    Java
    1.01
     java
    0.99
    JAVA
    0.96
     JDK
    0.96
     Javan
    0.93
    Oracle
    0.91
    java
    0.90
     Oracle
    0.90
    Activations Density 0.084%

    No Known Activations