© 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. 50386
    Prev
    Next
    INDEX
    Explanations

    engaged in companies

    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
    QUER
    -0.73
    畔
    -0.72
    Datasets
    -0.72
    garis
    -0.71
     sahiptir
    -0.71
     karş
    -0.71
    WindowConstants
    -0.70
    芹
    -0.69
    cteur
    -0.69
    äß
    -0.69
    POSITIVE LOGITS
     engaged
    4.69
    engaged
    3.77
     engage
    3.56
     involved
    3.55
     Engaged
    3.50
     engages
    3.23
    engage
    3.06
    Engage
    2.98
     Engage
    2.95
     engaging
    2.92
    Activations Density 0.102%

    No Known Activations