© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100985
    Prev
    Next
    INDEX
    Explanations

    Welsh places and geography

    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
    隐隐
    -1.05
     înainte
    -1.03
     dani
    -0.98
    嫔
    -0.97
     TextEditing
    -0.97
    ぐるみ
    -0.93
    namely
    -0.92
    ございません
    -0.92
    ",
    -0.91
    くちゃ
    -0.90
    POSITIVE LOGITS
     these
    1.04
    ).*
    1.02
     every
    1.02
    يور
    0.95
     this
    0.95
    你去
    0.91
    ftig
    0.91
    ILERS
    0.90
     puteți
    0.90
     terasa
    0.89
    Activations Density 0.059%

    No Known Activations