© 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. 22-GEMMASCOPE-RES-131K
    7. 128451
    Prev
    Next
    INDEX
    Explanations

    Ph.D

    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_22/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
    ៨
    -0.91
    []"
    -0.91
    UIControlState
    -0.90
     stili
    -0.90
     studia
    -0.89
     películas
    -0.88
     tärke
    -0.87
     leyendas
    -0.87
     ceremonia
    -0.85
    IEA
    -0.85
    POSITIVE LOGITS
    them
    0.86
    时
    0.82
     They
    0.81
     Row
    0.81
     Anytime
    0.80
    竞
    0.77
     قاشق
    0.76
     corresponds
    0.75
    `
    0.75
     Ab
    0.75
    Activations Density 0.020%

    No Known Activations