© 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. 34-GEMMASCOPE-RES-131K
    7. 64541
    Prev
    Next
    INDEX
    Explanations

    Tokyo Olympics postponed/delayed

    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
     ブログ
    -0.88
     gp
    -0.84
    componentWill
    -0.81
     Ponta
    -0.79
     hemis
    -0.74
    环节
    -0.70
     materia
    -0.69
     svn
    -0.68
    保育園
    -0.68
     doin
    -0.68
    POSITIVE LOGITS
     Tokyo
    1.82
    Tokyo
    1.54
    東京
    1.19
     東京
    1.13
     postponed
    1.11
     Paris
    1.05
     delayed
    1.04
     tokyo
    1.02
    TOKYO
    1.02
    东京
    0.97
    Activations Density 0.023%

    No Known Activations