© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65953
    Prev
    Next
    INDEX
    Explanations

    programming language imports and includes

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

    The neuron strongly activates on “import” statements (and to a lesser extent other top‐level declarations) 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_10/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
     
    -2.27
    }
    -2.08
     {
    -1.85
     there
    -1.73
    .
    -1.73
    s
    -1.72
    AT
    -1.66
     a
    -1.66
    t
    -1.64
    有
    -1.63
    POSITIVE LOGITS
    鑷
    1.81
    利
    1.77
     现场
    1.74
     또는
    1.71
     godziny
    1.67
    erráneo
    1.67
    橦
    1.67
    ığımız
    1.66
    年
    1.65
    彳
    1.63
    Activations Density 0.007%

    No Known Activations