© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32719
    Prev
    Next
    INDEX
    Explanations

    graph data structures

    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
     része
    -0.77
    љи
    -0.72
    镯
    -0.71
     screwing
    -0.70
    öhn
    -0.70
     getPassword
    -0.68
    bbies
    -0.67
    rieve
    -0.67
    Processo
    -0.67
    Actualmente
    -0.66
    POSITIVE LOGITS
     graph
    2.23
     vertex
    1.88
    graph
    1.87
     Graph
    1.85
    Graph
    1.81
     vertices
    1.72
     nodes
    1.72
     edge
    1.71
     network
    1.68
     graphs
    1.65
    Activations Density 0.145%

    No Known Activations