© 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. 919
    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
     összefoglal
    -1.10
    </h2>
    -1.06
     concerne
    -1.02
     início
    -1.01
    šinou
    -0.99
     összefoglaló
    -0.97
     sembl
    -0.96
    ipolar
    -0.95
    ABAD
    -0.90
     alkot
    -0.90
    POSITIVE LOGITS
     and
    0.98
    ,\\
    0.93
    过来了
    0.89
     normalerweise
    0.86
     rimasto
    0.86
    gay
    0.85
    ',
    0.83
    镯
    0.82
     diventato
    0.82
    metingen
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.