© 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. 67665
    Prev
    Next
    INDEX
    Explanations

    code and configuration imports

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

    The neuron strongly activates on programming-language import statements (the “import” keyword and its following module path).

    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
    `/
    -1.07
     tertarik
    -1.06
    řejmě
    -1.05
    univer
    -1.04
    CppMethod
    -1.03
    $<$
    -1.03
     solde
    -1.02
    ITÉ
    -1.02
     akci
    -1.01
     dirilis
    -0.99
    POSITIVE LOGITS
    д
    1.05
     лишь
    1.01
     способ
    1.00
    Allocate
    0.99
    ка
    0.97
    да
    0.97
    ken
    0.94
    InMemory
    0.93
     Hinsicht
    0.91
    0.90
    Activations Density 0.002%
    No Known Activations