© 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. 12010
    Prev
    Next
    INDEX
    Explanations

    sounds being heard

    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
    i
    -1.83
    ſelves
    -1.70
    m
    -1.55
     таким
    -1.51
    channel
    -1.46
     аналоги
    -1.46
    similar
    -1.45
     และ
    -1.41
    when
    -1.41
    ação
    -1.41
    POSITIVE LOGITS
    關注
    1.66
    不夠
    1.57
    越來
    1.52
    裡的
    1.51
     znovu
    1.48
    B
    1.43
    !");
    1.42
     escapes
    1.42
    将在
    1.40
     ネタ
    1.39
    Activations Density 0.012%

    No Known Activations