© 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. 101363
    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
     of
    -1.09
     customizations
    -1.05
     amazing
    -0.94
    爸爸
    -0.93
     recognizes
    -0.93
     way
    -0.91
     discover
    -0.91
    MANS
    -0.91
    geführten
    -0.89
     Vorte
    -0.88
    POSITIVE LOGITS
    鮟
    0.92
    🤾
    0.88
    nehå
    0.87
     ३
    0.87
     altid
    0.87
    
    0.86
    ási
    0.86
    Джере
    0.85
    isatie
    0.85
    ピン
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.