© 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. 48048
    Prev
    Next
    INDEX
    Explanations

    singleton instantiation patterns

    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
     migraines
    -0.89
    אים
    -0.77
    
    -0.71
     illum
    -0.70
    押
    -0.70
    СС
    -0.69
    得上
    -0.69
    raktion
    -0.68
    一的
    -0.68
     ravis
    -0.68
    POSITIVE LOGITS
     shared
    3.88
    shared
    3.55
    Shared
    2.84
     Shared
    2.84
    共享
    1.99
    SHARED
    1.95
     compartil
    1.94
    hared
    1.87
     partag
    1.81
     compartido
    1.77
    Activations Density 0.025%

    No Known Activations