© 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. 108103
    Prev
    Next
    INDEX
    Explanations

    plotting and graphing data

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron flags specialized, domain-specific jargon or key technical terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     muž
    -0.85
    koli
    -0.77
     verze
    -0.73
    veling
    -0.71
    >[
    -0.71
    struktur
    -0.70
    ítás
    -0.70
     cuadrados
    -0.69
    erik
    -0.69
    サイズ
    -0.68
    POSITIVE LOGITS
     graph
    5.09
     graphs
    4.91
    graph
    3.75
     plot
    3.72
     Graphs
    3.59
     Graph
    3.55
     plots
    3.55
    Graphs
    3.50
    Graph
    3.48
    graphs
    3.47
    Activations Density 0.154%

    No Known Activations