© 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. 22-GEMMASCOPE-RES-131K
    7. 67954
    Prev
    Next
    INDEX
    Explanations

    code and programming elements

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

    The neuron flags lines that bring external libraries or namespaces into a source file (import/include directives).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    atization
    -1.01
     prazo
    -1.00
    諼
    -0.97
    ätta
    -0.95
     ส์
    -0.95
     těchto
    -0.95
     estoque
    -0.93
    蛱
    -0.93
    抨
    -0.93
    ily
    -0.93
    POSITIVE LOGITS
     one
    1.11
     five
    1.05
     four
    0.99
     viera
    0.98
     would
    0.96
     líqu
    0.96
     in
    0.93
     three
    0.91
     two
    0.90
    دد
    0.90
    Activations Density 0.019%

    No Known Activations