© 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. 90889
    Prev
    Next
    INDEX
    Explanations

    Bahrain, bahn, bah

    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
    鼕
    -3.69
    潆
    -3.64
    
    -3.63
    makeat
    -3.53
     unſ
    -3.53
    毉
    -3.47
    colgante
    -3.42
     ซึ่ง
    -3.42
    廔
    -3.16
     iſt
    -3.14
    POSITIVE LOGITS
    (
    5.00
    s
    4.31
    on
    4.19
    u
    4.16
    V
    3.97
    n
    3.73
    W
    3.67
    In
    3.63
    C
    3.58
    m
    3.55
    Activations Density 0.003%

    No Known Activations