© 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. 109408
    Prev
    Next
    INDEX
    Explanations

    Broadway musical adaptations

    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
    enerbahçe
    -0.81
    拍攝
    -0.76
     analisar
    -0.73
     adelant
    -0.73
     unreleased
    -0.73
    这话
    -0.72
     atuação
    -0.70
     singled
    -0.70
    uss
    -0.69
    演技
    -0.69
    POSITIVE LOGITS
     music
    1.14
    adapted
    0.96
     lib
    0.96
    好看
    0.91
     музи
    0.90
    adaptor
    0.88
     songs
    0.86
    音楽
    0.86
    час
    0.85
    Adapted
    0.85
    Activations Density 0.025%

    No Known Activations