© 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. 22-GEMMASCOPE-RES-131K
    7. 69113
    Prev
    Next
    INDEX
    Explanations

    CSS properties and selectors

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

    The neuron fires on style‐ or layout‐related property–value assignments (for example CSS declarations like “border: 1px solid transparent;” or XML attributes such as android:state_focused="false").

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    CONCLUSIONES
    -1.11
    closure
    -1.10
    lieri
    -1.08
     englisch
    -1.07
    dures
    -1.07
    onner
    -1.04
     Před
    -1.04
    гам
    -1.04
    entreprise
    -1.03
     Czę
    -1.03
    POSITIVE LOGITS
    jangkau
    1.05
     когда
    1.02
    跟踪
    0.98
    使用方法
    0.98
    惹
    0.97
     собой
    0.96
    بسم
    0.95
     momentarily
    0.92
     radically
    0.91
    引言
    0.91
    Activations Density 0.002%

    No Known Activations