© 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. 11513
    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
    ियन
    -0.90
     Seguro
    -0.87
     tutup
    -0.86
     changements
    -0.84
     udah
    -0.84
     bieden
    -0.83
    られていた
    -0.81
    또
    -0.79
     gimana
    -0.79
    هرست
    -0.79
    POSITIVE LOGITS
    conte
    1.04
     strut
    0.99
     reorgan
    0.96
    omeness
    0.96
     judicial
    0.96
    的一
    0.94
     culinary
    0.93
     haremos
    0.92
     conseille
    0.91
    logna
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.