© 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. 45426
    Prev
    Next
    INDEX
    Explanations

    jar files and entries

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

    The neuron specializes in spotting references to Java archive resources—such as JAR file names, URLs, and manifest entries—embedded in code or XML.

    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
     Fuchs
    -0.93
     fotball
    -0.82
    FCA
    -0.79
    ⊥
    -0.77
    inctions
    -0.77
     Sunak
    -0.75
     сел
    -0.75
    Exer
    -0.73
     Surat
    -0.73
     Kanal
    -0.73
    POSITIVE LOGITS
     entry
    1.36
     entries
    1.34
    Entry
    1.27
    entry
    1.27
     Entry
    1.23
     ENTRY
    1.15
    ENTRY
    1.06
     Entries
    1.02
     Zip
    0.97
    entries
    0.94
    Activations Density 0.017%

    No Known Activations