© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60834
    Prev
    Next
    INDEX
    Explanations

    java package and version numbers

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

    This neuron activates on numeric tokens that denote software or document version numbers (e.g. license versions, PDFBox versions).

    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
     précédente
    -0.95
    蓓
    -0.89
     desarrolló
    -0.89
     llvm
    -0.88
    有無
    -0.87
    分明
    -0.86
     établissement
    -0.86
    其余
    -0.85
    ודם
    -0.83
     JAXBElement
    -0.82
    POSITIVE LOGITS
    final
    1.37
     Abstract
    1.25
    util
    1.09
    Abstract
    1.08
    continue
    0.98
     final
    0.96
    org
    0.96
    ≫
    0.94
    Default
    0.94
     org
    0.93
    Activations Density 0.065%

    No Known Activations