© 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. 34-GEMMASCOPE-RES-131K
    7. 92386
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    umentar
    -0.76
     Specifically
    -0.74
     дней
    -0.74
    Specifically
    -0.73
    chil
    -0.72
    setCustom
    -0.72
    ◇
    -0.72
     Раз
    -0.71
     Low
    -0.69
     Velvet
    -0.69
    POSITIVE LOGITS
    Appear
    0.78
     repercussions
    0.76
    lags
    0.75
     Đây
    0.75
    عت
    0.73
     Andri
    0.73
     exercícios
    0.71
    年龄
    0.71
     SRL
    0.71
    haft
    0.69
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.