© 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. 9967
    Prev
    Next
    INDEX
    Explanations

    winding up or wound

    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
     ‘’
    -2.48
     disposto
    -2.22
    簠
    -2.08
    
    -2.00
    ’’
    -2.00
    extrait
    -1.97
     zwischen
    -1.94
     somewhat
    -1.93
    during
    -1.92
     captivated
    -1.92
    POSITIVE LOGITS
    }$,
    2.28
    ículas
    2.03
     dotyczące
    2.00
     techniczne
    1.97
    TemporalType
    1.95
     With
    1.92
    膿
    1.91
     industrious
    1.90
    复古
    1.88
    諜
    1.84
    Activations Density 0.010%

    No Known Activations