© 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. 116812
    Prev
    Next
    INDEX
    Explanations

    zip and archive operations

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

    The neuron fires on mentions of compressing or zipping files—that is, any text or code calling out “compress”/“zip” operations on files.

    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
    uninstall
    -0.71
    Népesség
    -0.71
    折
    -0.69
     genoc
    -0.67
    侵略
    -0.65
     каль
    -0.65
    vom
    -0.65
    horm
    -0.64
     шан
    -0.64
     flicker
    -0.64
    POSITIVE LOGITS
     archive
    1.69
     Zip
    1.68
    zip
    1.52
    Zip
    1.50
     zipfile
    1.48
     ZIP
    1.46
    archive
    1.43
    compression
    1.42
    Archive
    1.39
     zip
    1.37
    Activations Density 0.059%

    No Known Activations