© 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. 22-GEMMASCOPE-RES-131K
    7. 15930
    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
    ровна
    -1.09
     ceremonia
    -1.03
    ！(
    -1.02
     sommar
    -1.02
     organisme
    -1.01
     teatro
    -0.98
     tragedia
    -0.97
    Применение
    -0.97
    IBLES
    -0.96
     Japon
    -0.96
    POSITIVE LOGITS
    ↵
    1.10
    łoży
    1.08
     gekauft
    1.05
    zulegen
    1.02
     aanzien
    1.02
     bepaald
    1.00
     звука
    1.00
     Эти
    0.98
     between
    0.98
    oceros
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.