© 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. 10-GEMMASCOPE-RES-131K
    7. 68316
    Prev
    Next
    INDEX
    Explanations

    canoes, kayaks, boats

    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
     fiables
    -1.34
    🧫
    -1.23
    Ꭳ
    -1.16
     perfecte
    -1.16
     deviennent
    -1.15
     supermercado
    -1.14
     deng
    -1.12
    搦
    -1.11
     було
    -1.10
     российский
    -1.10
    POSITIVE LOGITS
     इत
    1.31
        
    1.27
     shown
    1.23
    一是
    1.17
    とな
    1.17
     ακό
    1.13
     crucial
    1.13
    नलोड
    1.11
     mainly
    1.09
    主要是
    1.09
    Activations Density 0.023%

    No Known Activations