© 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. 97850
    Prev
    Next
    INDEX
    Explanations

    restoration and repairs

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects mentions of restoration or renovation (e.g. “restored,” “lovingly restored,” “has been restored”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     CHANGE
    -0.88
     النظام
    -0.85
     лесу
    -0.85
     די
    -0.83
     Change
    -0.83
     CHANGES
    -0.82
    CHANGE
    -0.80
    ()]);
    -0.80
    囔
    -0.79
     Changes
    -0.79
    POSITIVE LOGITS
     restoration
    5.31
     restored
    4.28
     restore
    4.28
     Restoration
    4.00
    Restoration
    3.83
     restoring
    3.69
    restore
    3.59
     restores
    3.50
     restorations
    3.48
    Restore
    3.25
    Activations Density 0.061%

    No Known Activations