© 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. 42472
    Prev
    Next
    INDEX
    Explanations

    excited to do something

    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
     on
    -2.16
     conventional
    -1.95
     frühen
    -1.76
     usual
    -1.73
     always
    -1.72
     should
    -1.71
     recommended
    -1.71
    还需要
    -1.67
     may
    -1.67
     your
    -1.66
    POSITIVE LOGITS
    nung
    1.88
     verbe
    1.84
     quai
    1.81
     inox
    1.78
    
    1.77
     uruguay
    1.76
     花纹
    1.74
     Itali
    1.73
     nage
    1.73
     mei
    1.70
    Activations Density 0.011%

    No Known Activations