© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83024
    Prev
    Next
    INDEX
    Explanations

    words that form compound concepts

    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
    engines
    -0.84
     infectious
    -0.79
    xml
    -0.79
     bonheur
    -0.76
     часов
    -0.76
    cub
    -0.75
    pathic
    -0.74
     ит
    -0.73
     deadly
    -0.73
    疾病
    -0.73
    POSITIVE LOGITS
     australian
    0.93
     community
    0.91
    yarakat
    0.89
    來
    0.88
    ierzch
    0.86
     bağlantılar
    0.86
    requested
    0.85
    genossen
    0.84
    PostInfinity
    0.84
     probablemente
    0.84
    Activations Density 0.020%

    No Known Activations