© 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. 10-GEMMASCOPE-RES-131K
    7. 69300
    Prev
    Next
    INDEX
    Explanations

    only, alone, or similar 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_10/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
     himself
    -1.79
     meneg
    -1.70
     melanjutkan
    -1.46
     memeriksa
    -1.45
     melap
    -1.43
     menambahkan
    -1.43
    umpulkan
    -1.41
     mengangg
    -1.41
     membag
    -1.41
    carian
    -1.38
    POSITIVE LOGITS
     only
    2.14
     herself
    1.91
     تنها
    1.65
    だけです
    1.60
     только
    1.45
    珐
    1.36
    dorfer
    1.34
     сама
    1.28
    üğü
    1.27
     רק
    1.26
    Activations Density 0.016%

    No Known Activations