© 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. 10-GEMMASCOPE-RES-131K
    7. 101683
    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
     mulighed
    -0.98
    During
    -0.95
    With
    -0.93
    kệ
    -0.92
    がありません
    -0.92
    bbled
    -0.91
    eward
    -0.89
    ⩩
    -0.89
     necesarias
    -0.87
    Before
    -0.85
    POSITIVE LOGITS
     éditoriale
    1.19
     phối
    1.04
     scènes
    1.03
     first
    1.03
    ']")
    0.96
    溏
    0.96
    OVID
    0.95
     ‘‘
    0.94
     clouded
    0.93
    ABU
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.