© 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. 2028
    Prev
    Next
    INDEX
    Explanations

    technical terms and their descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     exigen
    -0.96
     nutella
    -0.91
     peppa
    -0.91
     faggot
    -0.90
     veramente
    -0.88
     tỏi
    -0.88
    towany
    -0.86
    Minimize
    -0.85
    cupcake
    -0.85
    asına
    -0.85
    POSITIVE LOGITS
     its
    1.10
     ľ
    1.06
     belated
    0.99
    nalité
    0.98
     especiales
    0.94
     gdy
    0.92
    خوا
    0.91
     heavyweight
    0.90
     ください
    0.88
    жела
    0.87
    Activations Density 0.027%

    No Known Activations