© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81679
    Prev
    Next
    INDEX
    Explanations

    cluster, clusters, or k-means

    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
     entram
    -0.77
    Coaches
    -0.74
    exo
    -0.73
    rüstung
    -0.73
    casio
    -0.72
    jina
    -0.71
    prem
    -0.71
    Advisory
    -0.71
    scor
    -0.70
     Construcción
    -0.70
    POSITIVE LOGITS
     cluster
    1.79
     clusters
    1.52
     centers
    1.38
     Cluster
    1.34
    Cluster
    1.34
     cent
    1.34
    cluster
    1.30
    clusters
    1.16
     centro
    1.16
     Clusters
    1.15
    Activations Density 0.024%

    No Known Activations