© 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. 10-GEMMASCOPE-RES-131K
    7. 41730
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    筈
    -1.15
    苙
    -1.06
    碕
    -0.96
     нрави
    -0.96
     ᾿
    -0.95
     الفنان
    -0.93
    윽
    -0.93
    大好きな
    -0.92
    IANI
    -0.92
     echip
    -0.90
    POSITIVE LOGITS
     has
    1.10
     first
    1.05
     Richard
    1.02
    編曲
    0.98
     or
    0.96
    िने
    0.90
     GenerationType
    0.89
    яр
    0.88
     generates
    0.88
    barn
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.