© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118509
    Prev
    Next
    INDEX
    Explanations

    unsolved problems

    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
     pagal
    -1.05
    Purpose
    -0.94
     tà
    -0.93
     purpose
    -0.93
    què
    -0.91
     ané
    -0.90
    performed
    -0.88
     clavier
    -0.87
    ҳо
    -0.86
    purpose
    -0.85
    POSITIVE LOGITS
     solved
    2.50
    solved
    2.33
    解決
    2.06
     solve
    1.88
     solvable
    1.83
     Solved
    1.73
    resolved
    1.72
    解决
    1.71
     rozwią
    1.69
     megold
    1.68
    Activations Density 0.084%

    No Known Activations