© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 89703
    Prev
    Next
    INDEX
    Explanations

    restoring original state

    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
    htä
    -0.79
     especializada
    -0.78
    aragus
    -0.76
    다고
    -0.75
    ätzliche
    -0.75
     Administrativna
    -0.74
     especializados
    -0.72
    zufügen
    -0.71
    Só
    -0.71
     advancing
    -0.70
    POSITIVE LOGITS
    に戻
    2.17
     wieder
    2.00
     revert
    1.95
     reverted
    1.94
     original
    1.91
    恢复
    1.90
     normal
    1.88
    还原
    1.86
     restored
    1.80
     reverting
    1.80
    Activations Density 0.019%

    No Known Activations