© 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. 22-GEMMASCOPE-RES-131K
    7. 28526
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ⋉
    -1.07
    ",
    -0.96
     either
    -0.95
    =="
    -0.95
    只有
    -0.95
    =="")
    -0.94
    IANT
    -0.89
    !="")
    -0.88
     byen
    -0.87
    metria
    -0.86
    POSITIVE LOGITS
    órica
    1.12
    ítica
    1.08
    したので
    1.05
    ⾼
    1.05
    Bagi
    1.04
    Evet
    1.04
     lectura
    1.02
     melanjutkan
    1.00
    Андрей
    1.00
     continuation
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.