© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79535
    Prev
    Next
    INDEX
    Explanations

    import declarations

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

    This neuron detects import‐ or include‐style statements (e.g. "import …" or "#include …") in code.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     rand
    -0.87
     exceptions
    -0.84
    úde
    -0.83
     this
    -0.82
     thanks
    -0.80
     these
    -0.80
    SqlClient
    -0.80
     extends
    -0.78
     except
    -0.77
    a
    -0.77
    POSITIVE LOGITS
    Método
    1.00
    Lars
    0.87
    SOLUTION
    0.83
    €”
    0.82
    Almacen
    0.82
    Fetching
    0.82
     œufs
    0.81
     Pneumatic
    0.81
     Trunks
    0.81
    Finn
    0.81
    Activations Density 0.037%

    No Known Activations