© 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. 22-GEMMASCOPE-RES-131K
    7. 10942
    Prev
    Next
    INDEX
    Explanations

    eclipse configuration or study abroad

    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_22/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
    ƣ
    -1.12
     forro
    -1.08
     Técnicas
    -1.04
     mobilya
    -1.02
    entrega
    -1.02
    ＝＝＝＝
    -1.02
    comentario
    -1.01
     Crédito
    -1.00
    ＊＊＊＊
    -1.00
    InputBorder
    -1.00
    POSITIVE LOGITS
     College
    0.94
    o
    0.86
     .
    0.85
     ,
    0.85
    http
    0.84
    EXTENSION
    0.83
    
    0.83
                                   
    0.83
    窄
    0.82
    a
    0.81
    Activations Density 0.000%

    No Known Activations