© 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. 34-GEMMASCOPE-RES-131K
    7. 33289
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Hanya
    -0.97
    Cinta
    -0.94
    Matériel
    -0.91
     Pamph
    -0.89
     clique
    -0.88
    kommer
    -0.87
     alterations
    -0.87
    นี
    -0.86
    Choisissez
    -0.85
    Witaj
    -0.85
    POSITIVE LOGITS
     onze
    1.01
    kap
    0.97
     is
    0.96
     pianist
    0.91
    ße
    0.90
    ํ
    0.90
    🏀
    0.88
    eados
    0.88
    utate
    0.88
    ڤ
    0.88
    Activations Density 0.014%

    No Known Activations