© 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. 37891
    Prev
    Next
    INDEX
    Explanations

    imbue, imbric, imbalanced, Dibny, Kibble

    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
     lidí
    -0.78
     Badger
    -0.74
     heiress
    -0.74
    ujący
    -0.73
     regalías
    -0.73
    ומי
    -0.70
     svou
    -0.70
    
    -0.70
    шому
    -0.70
    philo
    -0.69
    POSITIVE LOGITS
     balance
    0.73
     imb
    0.72
     corn
    0.71
    vark
    0.70
     chod
    0.69
    Sortable
    0.69
    毫
    0.69
    hline
    0.69
     ceb
    0.69
     personal
    0.68
    Activations Density 0.022%

    No Known Activations