© 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. 3635
    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
     or
    -1.13
    usions
    -1.08
     dotyczące
    -1.05
    ũng
    -1.01
     with
    -0.96
    ítulos
    -0.95
     adulto
    -0.92
     swoje
    -0.92
     또는
    -0.91
     trovato
    -0.91
    POSITIVE LOGITS
     progressivement
    1.05
    хід
    0.90
     Think
    0.89
     スキ
    0.88
     كما
    0.88
    bitat
    0.88
     
    0.85
     disposição
    0.85
    随之
    0.85
     i
    0.83
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.