© 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. 19055
    Prev
    Next
    INDEX
    Explanations

    following conjunction

    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
    ,
    -1.98
     What
    -1.89
     with
    -1.68
     Some
    -1.64
     например
    -1.59
    ;
    -1.59
     That
    -1.55
     například
    -1.55
     One
    -1.54
     nuestras
    -1.49
    POSITIVE LOGITS
    鸲
    1.80
    屨
    1.77
    
    1.73
     BEER
    1.69
    ⩴
    1.68
     podemos
    1.64
     then
    1.62
     saranno
    1.57
     disposto
    1.56
    
    1.55
    Activations Density 0.025%

    No Known Activations