© 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. 23527
    Prev
    Next
    INDEX
    Explanations

    restoring power to customers

    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
     yearly
    -0.84
     llena
    -0.73
    perp
    -0.73
     océano
    -0.71
    serif
    -0.71
     horno
    -0.71
     ecológico
    -0.70
     videre
    -0.69
    arza
    -0.69
     fills
    -0.68
    POSITIVE LOGITS
     restoration
    2.19
     restore
    1.87
     outage
    1.82
    Restoration
    1.78
     Restoration
    1.76
     outages
    1.74
     restoring
    1.72
     restored
    1.65
     customers
    1.65
     restores
    1.63
    Activations Density 0.021%

    No Known Activations