© 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. 37856
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and points

    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_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
    jectures
    -0.82
    ▬▬▬▬
    -0.79
     comprimento
    -0.79
     RoutedEventArgs
    -0.77
     ormai
    -0.77
    が残
    -0.77
    quir
    -0.76
    兒童
    -0.75
    QUIR
    -0.75
     range
    -0.74
    POSITIVE LOGITS
    acán
    0.83
    又
    0.82
    рованного
    0.81
     maioria
    0.81
    POINT
    0.81
    Volatile
    0.80
    È
    0.79
     sings
    0.79
     haben
    0.78
     зданий
    0.77
    Activations Density 0.001%

    No Known Activations