© 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. 128003
    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
     Для
    -1.09
     alarme
    -1.00
     millon
    -0.98
     lemah
    -0.96
     formel
    -0.96
    Rather
    -0.94
     кух
    -0.94
     камен
    -0.93
    ступить
    -0.93
    🧴
    -0.93
    POSITIVE LOGITS
    我了
    1.10
     bursting
    1.09
     alrededores
    1.07
     czter
    1.05
     всеки
    1.04
    ୟ
    1.04
     you
    1.03
     conquering
    1.02
     какъ
    1.02
     blossoming
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.