© 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. 103370
    Prev
    Next
    INDEX
    Explanations

    long long

    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
    
    -1.99
    -1.87
    厛
    -1.86
    蟥
    -1.80
    喾
    -1.74
    ݮ
    -1.73
     برای
    -1.70
     родители
    -1.70
     asesinado
    -1.69
    ᡨ
    -1.67
    POSITIVE LOGITS
     of
    2.58
     —
    2.28
    淡淡的
    1.91
    ”
    1.86
    “
    1.86
    क्टर
    1.71
    n
    1.70
     sekä
    1.62
    そちら
    1.60
     并
    1.59
    Activations Density 0.001%

    No Known Activations