© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7217
    Prev
    Next
    INDEX
    Explanations

    included in this study

    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
    Those
    -2.05
     people
    -1.94
     four
    -1.76
    那些
    -1.70
     ingrained
    -1.68
     had
    -1.65
     someone
    -1.62
     something
    -1.62
     esos
    -1.61
    Some
    -1.59
    POSITIVE LOGITS
     this
    2.61
     dette
    1.82
     koel
    1.77
     bedien
    1.69
     nimmer
    1.64
     verhind
    1.63
    
    1.63
     小物
    1.54
     groet
    1.53
     schu
    1.53
    Activations Density 0.106%

    No Known Activations