© 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. 1989
    Prev
    Next
    INDEX
    Explanations

    questions starting with Q:

    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
     AttributeError
    -0.85
    몬
    -0.77
     diligently
    -0.76
     RoutedEventArgs
    -0.75
     Kiel
    -0.75
    iança
    -0.73
     steadily
    -0.72
    。」
    -0.72
    気
    -0.72
    madol
    -0.71
    POSITIVE LOGITS
    vailable
    0.88
    scribe
    0.86
     Также
    0.83
     също
    0.81
     keuntungan
    0.78
     também
    0.78
     valuables
    0.78
    owane
    0.77
    secution
    0.77
     ebenfalls
    0.77
    Activations Density 0.000%

    No Known Activations