© 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. 70442
    Prev
    Next
    INDEX
    Explanations

    stages of a process or level

    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
    ՚
    -2.06
    
    -1.68
    鰱
    -1.66
    也知道
    -1.66
     aldus
    -1.64
    ejemplo
    -1.64
    
    -1.63
     slechts
    -1.62
     intends
    -1.61
    恃
    -1.61
    POSITIVE LOGITS
    ar
    2.13
    ⚋
    1.82
    ol
    1.77
     причиной
    1.77
    y
    1.73
    袿
    1.72
     \%$
    1.67
    可以
    1.66
    ed
    1.63
     stages
    1.63
    Activations Density 0.046%

    No Known Activations