© 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. 59798
    Prev
    Next
    INDEX
    Explanations

    also, still, not, being

    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
     originalmente
    -1.99
     alluring
    -1.98
    DockStyle
    -1.85
     unbelievably
    -1.83
     unsettling
    -1.81
    ⑊
    -1.80
     ornate
    -1.79
     idyllic
    -1.77
     unn
    -1.77
    消失了
    -1.77
    POSITIVE LOGITS
     two
    2.30
    There
    2.28
     three
    2.14
    k
    2.02
    Just
    2.00
    Because
    1.98
    Not
    1.94
     There
    1.93
     five
    1.93
    While
    1.92
    Activations Density 0.003%

    No Known Activations