© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64012
    Prev
    Next
    INDEX
    Explanations

    possessive 's' followed by noun

    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
     same
    -0.98
    两
    -0.94
    けどね
    -0.93
    らしいです
    -0.93
    🎐
    -0.92
    と思われます
    -0.91
    tissimi
    -0.89
     similarly
    -0.89
     siena
    -0.87
    
    -0.86
    POSITIVE LOGITS
    に行ってきました
    1.04
     (@
    0.90
     Rating
    0.88
    営業時間
    0.88
     instagram
    0.88
    throp
    0.86
     intención
    0.86
    .'/
    0.86
     Ж
    0.86
     Blog
    0.86
    Activations Density 0.023%

    No Known Activations