© 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. 82847
    Prev
    Next
    INDEX
    Explanations

    License, Patent, households, RegExp

    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
     proposed
    -0.75
    ůže
    -0.73
    겨
    -0.72
    ulators
    -0.70
    )
    -0.69
    vec
    -0.68
     zorg
    -0.68
    emples
    -0.68
    Iniciar
    -0.68
     )
    -0.67
    POSITIVE LOGITS
    誇
    0.71
     ধ
    0.71
    
    0.67
     करता
    0.66
     Regent
    0.66
    setPage
    0.65
    逸
    0.65
    扩展
    0.65
     kata
    0.64
    EST
    0.64
    Activations Density 0.049%

    No Known Activations