© 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. 47515
    Prev
    Next
    INDEX
    Explanations

    rural China

    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
     Polski
    -0.96
     keel
    -0.94
    ffekt
    -0.94
     :)))
    -0.94
     峰
    -0.93
    ровать
    -0.93
    苯
    -0.93
     anci
    -0.93
    gania
    -0.92
     بوی
    -0.92
    POSITIVE LOGITS
    »،
    1.19
     observaciones
    1.10
    協議
    1.09
    倣
    1.05
     như
    1.00
     Änder
    0.99
    ”،
    0.99
     rapporti
    0.98
    धिक
    0.98
     Bestimm
    0.98
    Activations Density 0.015%

    No Known Activations