© 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. 103537
    Prev
    Next
    INDEX
    Explanations

    of whom/which

    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
    它们
    -1.81
    它們
    -1.62
     it
    -1.55
     itself
    -1.21
     оно
    -1.11
    它们的
    -1.05
     które
    -1.03
    どれも
    -1.01
    一つ
    -0.98
     which
    -0.98
    POSITIVE LOGITS
     who
    2.34
     whom
    1.80
    这些人
    1.71
     هؤلاء
    1.65
    全員
    1.56
     kteří
    1.48
     họ
    1.43
     którzy
    1.42
     آنان
    1.41
     Mereka
    1.41
    Activations Density 0.007%

    No Known Activations