© 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. 110668
    Prev
    Next
    INDEX
    Explanations

    names following common prefixes

    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
    辖
    -0.83
     Utiliz
    -0.82
    тивні
    -0.81
    líben
    -0.77
     africaine
    -0.75
     picnics
    -0.74
    ''
    -0.73
    ʖ
    -0.73
     theatres
    -0.73
    gique
    -0.73
    POSITIVE LOGITS
     hä
    0.79
    делать
    0.75
     timeline
    0.74
    kirch
    0.74
    heça
    0.73
     време
    0.73
    ।
    0.73
     setup
    0.73
    ête
    0.72
     Timeline
    0.71
    Activations Density 0.015%

    No Known Activations