© 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. 47640
    Prev
    Next
    INDEX
    Explanations

    as- words

    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
    縢
    -1.70
    complished
    -1.70
    ſſen
    -1.70
    なども
    -1.68
    dirond
    -1.67
    踯
    -1.66
    %;
    -1.62
    葎
    -1.62
    
    -1.61
    缡
    -1.61
    POSITIVE LOGITS
    ↵
    2.11
    s
    1.86
     Actually
    1.73
    最大
    1.68
     However
    1.66
     There
    1.64
     Moreover
    1.62
    The
    1.58
     Indeed
    1.55
     Unfortunately
    1.54
    Activations Density 0.027%

    No Known Activations