© 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. 85278
    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
    In
    -1.02
     legt
    -0.89
    ('../
    -0.88
    ₵
    -0.88
    别的
    -0.83
     характера
    -0.82
    eners
    -0.82
     linken
    -0.81
    Install
    -0.79
    グリーン
    -0.79
    POSITIVE LOGITS
     of
    1.11
     inmigrantes
    1.09
    vikling
    0.98
     chapter
    0.96
     cubanos
    0.96
    貽
    0.95
    ÊNCIA
    0.94
     refugiados
    0.93
     português
    0.93
     silently
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.