© 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. 22-GEMMASCOPE-RES-131K
    7. 70930
    Prev
    Next
    INDEX
    Explanations

    programming commands

    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
    드
    -0.98
    lighed
    -0.91
    spring
    -0.91
    ductors
    -0.90
     COMPANIES
    -0.90
     oye
    -0.89
    oung
    -0.88
    RSS
    -0.88
     アウター
    -0.88
    social
    -0.86
    POSITIVE LOGITS
     then
    1.09
    ShowDialog
    1.03
     will
    1.01
    缚
    1.01
    Largura
    0.98
     рассказала
    0.96
    그리고
    0.95
    Every
    0.95
     нази
    0.94
    に行ってきました
    0.93
    Activations Density 0.004%

    No Known Activations