© 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. 48660
    Prev
    Next
    INDEX
    Explanations

    Swift UI code

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

    This neuron responds to code‐like syntax elements—especially programming tokens such as HTML tag delimiters (“<”), CSS/property identifiers, and other code keywords.

    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
    ListTile
    -0.91
    TextFormField
    -0.88
     TextFormField
    -0.87
     after
    -0.84
    sene
    -0.78
    béco
    -0.77
    borderBottom
    -0.77
     ListTile
    -0.76
     within
    -0.76
    ldorf
    -0.76
    POSITIVE LOGITS
    Expanded
    1.14
     IconButton
    1.08
    IconButton
    1.02
    Flexible
    1.00
     Circle
    0.97
     Expanded
    0.94
     flexible
    0.93
    oul
    0.91
     Flexible
    0.91
    Spacer
    0.90
    Activations Density 0.001%

    No Known Activations