© 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. 85819
    Prev
    Next
    INDEX
    Explanations

    online platforms and services

    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
     That
    -2.02
     shows
    -1.88
     However
    -1.80
     Instead
    -1.79
    有三
    -1.78
     biografia
    -1.77
     icona
    -1.73
     tampaknya
    -1.70
     we
    -1.70
     Compared
    -1.67
    POSITIVE LOGITS
    them
    2.11
    
    1.98
    蓠
    1.91
    didSet
    1.88
    板块
    1.77
    ଃ
    1.77
    sizeCache
    1.76
     sizzling
    1.71
    它们的
    1.70
    €“
    1.68
    Activations Density 0.007%

    No Known Activations