© 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. 84114
    Prev
    Next
    INDEX
    Explanations

    covered or coated

    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
    cinations
    -0.73
     Anlagen
    -0.69
     polymers
    -0.69
    kozások
    -0.69
    ipients
    -0.69
    Calculating
    -0.68
    ứa
    -0.68
    ▚
    -0.67
     Confederacy
    -0.67
    sierra
    -0.67
    POSITIVE LOGITS
     covered
    4.03
    covered
    3.58
     Covered
    3.11
    Covered
    3.09
     coated
    2.00
     COVER
    1.88
     покры
    1.85
     clad
    1.82
     covering
    1.72
    coated
    1.71
    Activations Density 0.072%

    No Known Activations