© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8900
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    
    -1.13
     accesorios
    -1.05
     القلب
    -1.04
     favoritas
    -1.01
    setAddress
    -1.00
    oldest
    -1.00
    childrens
    -1.00
     primeiros
    -0.97
    pulsera
    -0.96
     seguido
    -0.96
    POSITIVE LOGITS
    on
    0.93
     Люди
    0.88
     jeweiligen
    0.88
    載
    0.86
    Materiale
    0.85
     Одна
    0.85
     Конечно
    0.84
     entsprechende
    0.84
    alisis
    0.84
     bloss
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.