© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91344
    Prev
    Next
    INDEX
    Explanations

    theme and style

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

    The neuron activates on Android styling and resource‐attribute code—e.g. style/styleable declarations, values XML, TypedArray and obtainStyledAttributes calls.

    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
     Mesozoic
    -0.82
    clipboard
    -0.82
     vox
    -0.79
     aliphatic
    -0.75
     with
    -0.73
    嚐
    -0.71
     WQS
    -0.71
     saws
    -0.70
    énus
    -0.70
     đa
    -0.69
    POSITIVE LOGITS
     theme
    1.55
     themes
    1.24
    Theme
    1.20
     Theme
    1.16
     themed
    1.13
     тему
    1.12
    theme
    1.09
    主题
    1.06
     thèmes
    1.00
     temática
    0.97
    Activations Density 0.001%

    No Known Activations