© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26998
    Prev
    Next
    INDEX
    Explanations

    code includes and namespaces

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

    The neuron fires on lines that bring external modules or headers into code (e.g. import, include, using/namespace 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
    */;
    -0.92
     mármol
    -0.90
     =[
    -0.89
    []);
    -0.88
     as
    -0.88
    cot
    -0.88
    ｘ
    -0.86
    uló
    -0.82
    usion
    -0.82
     Jones
    -0.82
    POSITIVE LOGITS
    Iš
    1.12
    arım
    1.10
     cemented
    1.06
    Leírás
    1.01
     xăm
    1.01
    Penjelasan
    0.99
    ごま
    0.93
    Gonzalez
    0.91
     Pièces
    0.91
    あー
    0.91
    Activations Density 0.041%

    No Known Activations