© 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. 66825
    Prev
    Next
    INDEX
    Explanations

    Pakistan Navy

    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
     just
    -0.98
     pertama
    -0.90
     gesamte
    -0.90
     so
    -0.86
     for
    -0.85
    obenzene
    -0.85
     this
    -0.83
     really
    -0.82
     quite
    -0.82
     first
    -0.81
    POSITIVE LOGITS
    渲染
    0.87
    Чтоб
    0.85
     adolescentes
    0.85
    ורים
    0.85
     outliers
    0.84
    шити
    0.84
     capitales
    0.83
    chrome
    0.82
     getNombre
    0.82
     adolescente
    0.81
    Activations Density 0.006%

    No Known Activations