© 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. 103918
    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
    窣
    -1.08
    ñores
    -0.99
    阳台
    -0.97
     Países
    -0.96
     から
    -0.95
    izability
    -0.94
     bandeja
    -0.93
    bró
    -0.90
    ussy
    -0.89
     novio
    -0.89
    POSITIVE LOGITS
     Here
    0.98
    \'
    0.91
    ALIA
    0.87
    Calcul
    0.86
    npos
    0.85
    fated
    0.82
     הוא
    0.82
     části
    0.82
    ственным
    0.81
    gga
    0.78
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.