© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100963
    Prev
    Next
    INDEX
    Explanations

    wishes and desires

    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_10/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
     existing
    -1.98
     $
    -1.72
    vantaged
    -1.56
    神器
    -1.55
     access
    -1.55
     available
    -1.54
    秝
    -1.51
     existentes
    -1.45
    糶
    -1.43
     use
    -1.42
    POSITIVE LOGITS
    咙
    1.66
     که
    1.54
     Endlich
    1.51
     Undoubtedly
    1.44
     Nevertheless
    1.44
    Barang
    1.41
    cloudf
    1.34
     سانتی
    1.34
    --
    1.34
     Ours
    1.34
    Activations Density 0.004%

    No Known Activations