© 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. 90117
    Prev
    Next
    INDEX
    Explanations

    numerical data and percentages

    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
     recommended
    -0.99
     RECOMMENDED
    -0.82
    Recommended
    -0.79
     different
    -0.77
     whom
    -0.77
     Recommended
    -0.76
     mandatory
    -0.75
    服务的
    -0.73
    *{
    -0.72
    utorial
    -0.71
    POSITIVE LOGITS
     FET
    0.81
    欣
    0.80
    교
    0.78
    LabelTagHelper
    0.75
     כת
    0.73
     FRP
    0.73
    скі
    0.72
     ガー
    0.72
     ICD
    0.71
     alguém
    0.71
    Activations Density 0.025%

    No Known Activations