© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60721
    Prev
    Next
    INDEX
    Explanations

    top and bottom

    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
     також
    -1.78
     üblichen
    -1.68
     veranderen
    -1.67
    
    -1.58
     bereiken
    -1.54
    ujuk
    -1.54
    缥
    -1.53
     ACKNOWLEDGMENTS
    -1.46
     and
    -1.45
     bocas
    -1.44
    POSITIVE LOGITS
    ，
    1.66
    。
    1.62
     своего
    1.60
     estoy
    1.54
    k
    1.53
    の作成
    1.51
    f
    1.49
    t
    1.47
    ст
    1.45
    satunya
    1.45
    Activations Density 0.057%

    No Known Activations