© 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. 129144
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on the literal module names (the path or package identifiers) in import/require statements.

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

    relative imports

    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
     TÉCNICA
    -1.34
     aplique
    -1.27
     znaleźć
    -1.12
     його
    -1.08
     these
    -1.08
    Identyfik
    -1.07
    jącej
    -1.07
     allow
    -1.06
     до
    -1.05
     haphazard
    -1.05
    POSITIVE LOGITS
     """
    1.29
     './
    1.22
     fars
    1.16
     ._
    1.15
     ""
    1.14
    >
    1.13
     سات
    1.09
     They
    1.09
    怎么回事
    1.06
     *__
    1.05
    Activations Density 0.006%

    No Known Activations