© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25979
    Prev
    Next
    INDEX
    Explanations

    code inheritance and inclusion

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

    The neuron detects lines that invoke or declare inclusion/extension of external modules or templates (e.g. “extends,” “load,” “import,” “include,” etc.).

    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
     Again
    -1.04
     manchmal
    -1.02
    幾天
    -0.96
     again
    -0.95
     데이터
    -0.94
    なあ
    -0.93
     to
    -0.91
     these
    -0.90
     Gründung
    -0.90
     Vertreter
    -0.89
    POSITIVE LOGITS
     novios
    1.17
    nvarchar
    1.10
    rceil
    1.09
    ств
    1.09
    vár
    1.08
     vengo
    1.05
     Bá
    1.05
     coute
    1.02
    mlı
    1.00
     conférence
    1.00
    Activations Density 0.022%

    No Known Activations