© 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. 34-GEMMASCOPE-RES-131K
    7. 109618
    Prev
    Next
    INDEX
    Explanations

    unique, another, or latest items

    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_34/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
     siè
    -1.38
     plafon
    -1.37
    issime
    -1.31
    
    -1.27
    瘣
    -1.27
     échanti
    -1.27
    uded
    -1.26
    ܆
    -1.26
    졍
    -1.25
    truly
    -1.23
    POSITIVE LOGITS
     noteworthy
    1.87
     notable
    1.68
     impressive
    1.62
     unusual
    1.58
     remarkable
    1.48
     important
    1.48
     similarly
    1.46
     prominent
    1.42
     related
    1.39
     changes
    1.36
    Activations Density 0.074%

    No Known Activations