© 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. 15944
    Prev
    Next
    INDEX
    Explanations

    import statements

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

    The neuron specializes in spotting import statements (the “import” keyword and associated package path tokens) in code.

    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
     Gunakan
    -1.07
    そして
    -1.05
    [:,:,
    -1.02
     Menggunakan
    -1.02
     HasFactory
    -1.02
     Namun
    -1.02
     Pakai
    -1.02
    
    -1.01
    ſſen
    -1.01
     Penggunaan
    -1.00
    POSITIVE LOGITS
    ACIÓN
    1.02
     ธ
    1.02
     básicamente
    1.01
     algemene
    1.00
    達が
    0.99
    ほら
    0.97
     همیشه
    0.93
    넌
    0.93
     científico
    0.93
    是一款
    0.93
    Activations Density 0.061%

    No Known Activations