© 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. 130897
    Prev
    Next
    INDEX
    Explanations

    relief

    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
     inspiring
    -1.66
     był
    -1.63
    '
    -1.62
     zapewnia
    -1.61
     this
    -1.57
     as
    -1.57
     était
    -1.55
     its
    -1.52
     eight
    -1.52
     angry
    -1.48
    POSITIVE LOGITS
    だけではなく
    1.80
    狳
    1.70
    だけでなく
    1.70
    4
    1.70
     Será
    1.61
    ikes
    1.60
    
    1.59
     herausgegeben
    1.59
    很是
    1.58
     mentre
    1.56
    Activations Density 0.016%

    No Known Activations