© 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. 4179
    Prev
    Next
    INDEX
    Explanations

    exclusively

    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
     khác
    -1.02
     manchmal
    -0.95
     từng
    -0.90
    可以在
    -0.89
     często
    -0.88
     Особенно
    -0.87
     особенно
    -0.87
     часто
    -0.86
     Especially
    -0.86
     appena
    -0.86
    POSITIVE LOGITS
     exclusively
    3.81
    exclu
    3.17
     Exclu
    2.58
     exclusivamente
    2.50
     exclusive
    2.50
     exclu
    2.38
     EXCLUS
    2.34
    Exclu
    2.33
     exclusivement
    2.31
    exclusive
    2.23
    Activations Density 0.110%

    No Known Activations