© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 128896
    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
    ”-
    -0.98
    :");
    
    -0.95
    -”
    -0.94
    !")
    
    -0.93
    !");
    
    -0.92
    -“
    -0.91
     vins
    -0.91
     astu
    -0.88
     pernic
    -0.88
    รวจ
    -0.88
    POSITIVE LOGITS
     obyvateľov
    1.00
     Reform
    0.94
    bahaya
    0.94
     ženy
    0.94
    vallen
    0.93
     mencionado
    0.92
    quait
    0.89
    flowered
    0.88
     mencionados
    0.88
    joven
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.