© 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. 22-GEMMASCOPE-RES-131K
    7. 39576
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Wikipédia
    -1.08
    いため
    -1.07
     auge
    -1.02
     vernis
    -0.99
     fré
    -0.99
     trase
    -0.98
    Spenden
    -0.97
    Джере
    -0.97
    鯔
    -0.96
     subi
    -0.94
    POSITIVE LOGITS
    odeficiency
    0.93
    天气
    0.88
    igeon
    0.88
     совсем
    0.85
    jandro
    0.85
     First
    0.85
     ไม่
    0.84
    ğimiz
    0.83
    PyExc
    0.82
     tinha
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.