© 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. 10-GEMMASCOPE-RES-131K
    7. 9826
    Prev
    Next
    INDEX
    Explanations

    library/framework code structure

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

    The neuron fires on the names of packages/modules/namespaces (the identifiers in import, package, using, or namespace declarations).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     four
    -1.67
     two
    -1.57
     with
    -1.52
     имеются
    -1.52
     keinem
    -1.44
     three
    -1.44
     from
    -1.42
     five
    -1.36
    ソリン
    -1.34
     in
    -1.30
    POSITIVE LOGITS
     rojas
    1.66
    躥
    1.55
    ING
    1.52
     faim
    1.47
    最近
    1.47
    libatkan
    1.45
    最新
    1.44
    şan
    1.41
     inspiradoras
    1.41
     rús
    1.41
    Activations Density 0.112%

    No Known Activations