© 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. 48040
    Prev
    Next
    INDEX
    Explanations

    background property binding

    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
    ogenesis
    -0.79
     daniel
    -0.74
    確認ください
    -0.73
    ჰ
    -0.73
    فهوم
    -0.71
     criou
    -0.71
    χι
    -0.70
    anthe
    -0.69
    当地
    -0.69
     Tây
    -0.68
    POSITIVE LOGITS
     background
    1.44
     Background
    1.41
     binding
    1.39
    Background
    1.30
     Binding
    1.27
    background
    1.17
    binding
    1.13
     BACKGROUND
    1.11
    BACKGROUND
    1.10
    Binding
    1.05
    Activations Density 0.005%

    No Known Activations