© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60040
    Prev
    Next
    INDEX
    Explanations

    CSS properties and units

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

    The neuron is keyed to CSS style declarations, especially picking up the property‐value tokens (notably numeric values and alignment keywords) in CSS blocks.

    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
    ethyl
    -0.78
    細
    -0.75
     Submitted
    -0.75
    getSelectedItem
    -0.75
    关
    -0.73
    
    -0.73
    أس
    -0.72
     قطاع
    -0.71
     सेमी
    -0.70
     Change
    -0.70
    POSITIVE LOGITS
    Amical
    0.86
    hadores
    0.85
     Tribut
    0.85
    叟
    0.82
    Kde
    0.80
    书法
    0.79
     Gillette
    0.77
    嗗
    0.76
    Meld
    0.76
    Nye
    0.76
    Activations Density 0.002%

    No Known Activations