© 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. 129496
    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
    gelijk
    -1.02
    Thumb
    -1.02
     vulga
    -0.98
    gelijke
    -0.96
     kring
    -0.94
    ulico
    -0.92
      “
    -0.91
     diga
    -0.90
     nena
    -0.90
     paradis
    -0.90
    POSITIVE LOGITS
     jugó
    1.10
    ablanca
    1.00
     deutschen
    0.99
     vorigen
    0.98
    zzet
    0.96
     appartamento
    0.94
     effectiveness
    0.93
     rg
    0.93
     之
    0.93
     June
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.