© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22735
    Prev
    Next
    INDEX
    Explanations

    downloading content or apps

    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
    Negative Logits
     you
    -2.08
     When
    -1.80
    Those
    -1.76
    S
    -1.62
    section
    -1.60
     所以
    -1.55
    s
    -1.51
     alguien
    -1.50
     with
    -1.48
    All
    -1.47
    POSITIVE LOGITS
    奩
    1.79
    vedades
    1.77
    bisa
    1.76
    眛
    1.76
     délais
    1.74
     soportes
    1.74
     welchem
    1.73
    ᯾
    1.66
     favoris
    1.63
    抔
    1.61
    Activations Density 0.022%

    No Known Activations