© 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. 58972
    Prev
    Next
    INDEX
    Explanations

    foreign names

    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
     after
    -1.00
     especially
    -0.93
     приготовить
    -0.90
     就
    -0.83
     should
    -0.82
     where
    -0.81
    biases
    -0.79
     like
    -0.79
    西方
    -0.79
     What
    -0.78
    POSITIVE LOGITS
     ancora
    1.05
    terne
    1.02
     konstruk
    0.95
    vitis
    0.95
     dokumenta
    0.94
     farmacé
    0.94
    becue
    0.94
    Править
    0.94
     مفت
    0.93
    URLEncoder
    0.92
    Activations Density 0.033%

    No Known Activations