© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93535
    Prev
    Next
    INDEX
    Explanations

    programming identifiers and syntax

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

    This neuron detects JavaScript-style object property access using the dot operator (e.g., obj.selectedIndex).

    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
    "),
    
    -0.93
     )
    
    -0.91
    pography
    -0.90
     harmonie
    -0.90
     ){
    -0.89
    "):
    -0.88
     );
    
    -0.88
     );
    -0.88
    wod
    -0.85
     <",
    -0.83
    POSITIVE LOGITS
     этих
    1.00
    Idx
    0.92
    หมือน
    0.91
     These
    0.90
    感じが
    0.89
    看來
    0.88
     ervan
    0.88
    Index
    0.87
    های
    0.85
    stanley
    0.85
    Activations Density 0.010%

    No Known Activations