© 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. 34-GEMMASCOPE-RES-131K
    7. 58490
    Prev
    Next
    INDEX
    Explanations

    code examples and various languages

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

    The neuron strongly activates on code lines that define array/list literals (i.e. square-bracket initializations).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     ridges
    -0.94
     Ersten
    -0.88
    rics
    -0.88
     and
    -0.85
    pirable
    -0.81
     issues
    -0.81
    TabView
    -0.80
     kwiat
    -0.80
     kimse
    -0.79
     Hingga
    -0.79
    POSITIVE LOGITS
    +[
    0.97
     качестве
    0.90
     cualquier
    0.86
     funktioniert
    0.86
    سر
    0.82
     алгорит
    0.82
    toplasmic
    0.82
    //-->
    0.81
    </h4>
    0.79
    =[],
    0.78
    Activations Density 0.016%

    No Known Activations