© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73804
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
    unanje
    -1.06
    lový
    -1.05
    lové
    -1.04
     Ofrece
    -0.95
    älj
    -0.91
    éticos
    -0.91
    lné
    -0.91
    
    -0.90
    笑意
    -0.90
    leyebilirsiniz
    -0.90
    POSITIVE LOGITS
     and
    0.86
     kişilik
    0.83
    Glossary
    0.82
     geschenk
    0.80
     saa
    0.77
    atlan
    0.76
    Dise
    0.75
     Große
    0.75
    дам
    0.74
    set
    0.74
    Activations Density 0.059%

    No Known Activations