© 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. 55929
    Prev
    Next
    INDEX
    Explanations

    code initialization and closing tags

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Politics
    -0.89
     Direito
    -0.83
    vinilo
    -0.82
    dür
    -0.81
     it
    -0.81
    PointF
    -0.81
    slf
    -0.79
     this
    -0.79
     that
    -0.77
     bunun
    -0.77
    POSITIVE LOGITS
     initialize
    1.00
    initialize
    0.96
    void
    0.90
     关闭
    0.86
     initialized
    0.85
     adieu
    0.81
    初始化
    0.81
     eft
    0.80
    Repe
    0.79
    Initializing
    0.78
    Activations Density 0.003%

    No Known Activations