© 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. 119080
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
     still
    -0.90
     probablemente
    -0.82
     testar
    -0.75
    糾
    -0.74
     useful
    -0.72
    ixeira
    -0.71
    camin
    -0.71
    Кому
    -0.70
     Gesundheit
    -0.69
     add
    -0.69
    POSITIVE LOGITS
    JOptionPane
    0.98
    Scanner
    0.96
     сооб
    0.95
    Relationships
    0.94
    MENU
    0.93
     menu
    0.91
     меню
    0.87
    endurch
    0.87
    גת
    0.87
     MENU
    0.85
    Activations Density 0.006%

    No Known Activations