© 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. 34-GEMMASCOPE-RES-131K
    7. 83037
    Prev
    Next
    INDEX
    Explanations

    AssemblyCulture attribute

    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_34/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
    ��������
    -0.94
    天皇
    -0.79
     LIBRAR
    -0.75
    Http
    -0.75
    ����
    -0.75
     scones
    -0.73
     bishops
    -0.73
    琀
    -0.72
    क्
    -0.72
     Cardboard
    -0.72
    POSITIVE LOGITS
     next
    0.82
     귀
    0.81
     exemplu
    0.79
     dó
    0.76
    的多
    0.73
     Sö
    0.73
    maktadır
    0.73
    堇
    0.73
    olester
    0.71
     Offset
    0.71
    Activations Density 0.000%

    No Known Activations