© 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. 116598
    Prev
    Next
    INDEX
    Explanations

    database tables and keys

    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
    的对象
    -0.85
    ayuda
    -0.84
    色々な
    -0.82
     Estelle
    -0.81
     globo
    -0.80
    followed
    -0.78
    Рейтинг
    -0.78
    全体的に
    -0.77
     another
    -0.75
    }{||
    -0.74
    POSITIVE LOGITS
     vás
    0.94
    pkey
    0.91
     рем
    0.84
     translations
    0.83
     by
    0.82
     fatalities
    0.80
    вной
    0.80
    ęć
    0.80
     гель
    0.79
    SocketChannel
    0.79
    Activations Density 0.026%

    No Known Activations