© 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. 65384
    Prev
    Next
    INDEX
    Explanations

    image paths and urls

    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
    อ่าน
    -0.77
    gbarkeit
    -0.75
     pym
    -0.72
    小编
    -0.71
     dryness
    -0.69
     möjlighet
    -0.69
     Tj
    -0.68
    好用
    -0.67
     emigrants
    -0.67
    で見る
    -0.67
    POSITIVE LOGITS
    assets
    1.57
     assets
    1.50
     require
    1.48
    require
    1.38
     "./
    1.38
     https
    1.37
    https
    1.36
     Assets
    1.32
     './
    1.32
     "/
    1.31
    Activations Density 0.014%

    No Known Activations