© 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. 34-GEMMASCOPE-RES-131K
    7. 91568
    Prev
    Next
    INDEX
    Explanations

    window hierarchy

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

    The neuron fires on structural code‐definition tokens (imports, class/func/var keywords, colons, inheritance and type annotations) characteristic of Swift/Objective-C declarations.

    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
    adona
    -0.78
    חק
    -0.77
    WOL
    -0.76
     welt
    -0.72
    ciens
    -0.70
    Thermo
    -0.70
    缽
    -0.69
    ₦
    -0.69
    ้อน
    -0.69
     espin
    -0.69
    POSITIVE LOGITS
     UIApplication
    1.59
     window
    1.55
    UIApplication
    1.54
    window
    1.42
     Window
    1.34
    Window
    1.33
     windows
    1.25
    MainWindow
    1.12
    WINDOW
    1.10
     key
    1.06
    Activations Density 0.071%

    No Known Activations