© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3352
    Prev
    Next
    INDEX
    Explanations

    The neuron detects software version strings and related numeric version references (e.g. Java/JDK version numbers).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Watertown
    0.64
     पंजाबी
    0.57
    瑞
    0.56
    Bool
    0.55
    蛯
    0.55
    Beg
    0.55
    闾
    0.55
    蕁
    0.55
    新潟
    0.54
    MsgCallBack
    0.54
    POSITIVE LOGITS
     javafx
    1.22
     jdk
    1.20
    javafx
    1.05
     JDK
    0.97
     java
    0.94
    jdk
    0.93
    orElse
    0.91
    Javadoc
    0.82
     LocalDate
    0.82
    openjdk
    0.82
    Activations Density 0.019%

    No Known Activations