© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102487
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
     також
    -1.67
    ifiquement
    -1.54
     latas
    -1.54
    ”,
    -1.50
     morena
    -1.48
     invigor
    -1.48
     WaitForSeconds
    -1.47
     rejuven
    -1.47
     longstanding
    -1.45
     paradigma
    -1.45
    POSITIVE LOGITS
    訁
    1.91
        
    1.56
     Anſ
    1.54
    {
    1.53
    这个
    1.53
     Añade
    1.48
     prossima
    1.45
     Obtén
    1.41
     foremost
    1.40
     României
    1.40
    Activations Density 0.003%

    No Known Activations