© 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. 128174
    Prev
    Next
    INDEX
    Explanations

    The neuron flags occurrences of the keyword “import,” as seen in import statements in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    technical imports and names

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ПК
    -1.20
     valentín
    -1.18
    ñales
    -1.17
     biblia
    -1.16
    شهر
    -1.13
     levé
    -1.13
     plafon
    -1.13
     évé
    -1.10
     carga
    -1.10
     ceremonia
    -1.09
    POSITIVE LOGITS
     Various
    1.16
     and
    1.05
     gleichen
    1.00
    3
    0.98
     various
    0.96
     различные
    0.95
     different
    0.94
     anderer
    0.92
    兩種
    0.91
     Former
    0.91
    Activations Density 0.000%

    No Known Activations