© 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. 48119
    Prev
    Next
    INDEX
    Explanations

    commands and automation

    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
    mika
    -0.77
    ADIAN
    -0.77
     egip
    -0.74
    compens
    -0.72
    \\
    -0.71
    ReadInt
    -0.71
    aI
    -0.70
     Monastery
    -0.70
     wires
    -0.70
    cours
    -0.69
    POSITIVE LOGITS
    Automation
    0.75
     نعم
    0.71
     Customized
    0.71
     प्रद
    0.69
    Commands
    0.69
    IPL
    0.68
    パフォーマンス
    0.68
     Customization
    0.67
    Wildcard
    0.67
    URER
    0.66
    Activations Density 0.023%

    No Known Activations