© 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. 10-GEMMASCOPE-RES-131K
    7. 130549
    Prev
    Next
    INDEX
    Explanations

    Philadelphia, Bama, Physical, Chhoti Diwali

    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_10/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
    ↵↵
    -2.28
    
    -2.16
     anden
    -2.14
    (
    -2.06
    要
    -2.03
    at
    -2.02
     encantado
    -2.02
    .
    -1.95
     frescas
    -1.94
     enticing
    -1.94
    POSITIVE LOGITS
     were
    2.52
    我又
    2.13
    泚
    2.02
     fuimos
    2.00
    なども
    1.98
    癀
    1.98
     ricorda
    1.98
     quedan
    1.97
     pasamos
    1.97
     mehrere
    1.95
    Activations Density 0.004%

    No Known Activations