© 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. 110499
    Prev
    Next
    INDEX
    Explanations

    address label

    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
     requisite
    -2.09
     一
    -1.87
     Hinblick
    -1.85
    蓠
    -1.84
    
    -1.79
     shriek
    -1.78
    嵛
    -1.77
    
    -1.76
    傒
    -1.75
     somewhat
    -1.74
    POSITIVE LOGITS
     после
    1.88
     address
    1.81
    ープン
    1.77
    Nuestros
    1.68
    -
    1.67
    قدام
    1.62
     give
    1.60
     develop
    1.60
     eliminate
    1.59
    煐
    1.58
    Activations Density 0.027%

    No Known Activations