© 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. 10-GEMMASCOPE-RES-131K
    7. 3775
    Prev
    Next
    INDEX
    Explanations

    province geographical locations

    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
    檮
    -2.92
     unſ
    -2.66
     westfalen
    -2.44
    齜
    -2.38
     sprüche
    -2.34
    鐿
    -2.27
    蟊
    -2.23
    ciutto
    -2.23
    鰱
    -2.22
    還沒
    -2.20
    POSITIVE LOGITS
    vantaged
    2.69
    瑧
    2.48
    m
    2.39
    崛
    2.39
    It
    2.36
     of
    2.36
    micamente
    2.28
    鸰
    2.28
    ↵↵
    2.25
    籏
    2.25
    Activations Density 0.005%

    No Known Activations