© 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. 66076
    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
    edm
    -0.93
     your
    -0.91
    LO
    -0.91
    rü
    -0.91
     ficar
    -0.88
    your
    -0.88
     termen
    -0.88
     препят
    -0.88
     Для
    -0.88
     工
    -0.87
    POSITIVE LOGITS
     even
    1.18
    ⌑
    1.13
    девушка
    1.01
    variations
    0.96
    ندما
    0.94
     as
    0.91
     similar
    0.91
     so
    0.91
     dictadura
    0.90
     variations
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.