© 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. 32401
    Prev
    Next
    INDEX
    Explanations

    industry hubs and clusters

    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
     verwendeten
    -0.85
    adomo
    -0.85
    popularity
    -0.84
    ykite
    -0.84
    ῆς
    -0.81
    üme
    -0.79
     supermarket
    -0.77
    Popular
    -0.76
    вій
    -0.74
     مدير
    -0.74
    POSITIVE LOGITS
     cluster
    1.80
     clusters
    1.70
    cluster
    1.48
    clustering
    1.45
     Cluster
    1.44
     clustering
    1.39
    Clusters
    1.35
    Cluster
    1.33
     firms
    1.30
     companies
    1.30
    Activations Density 0.042%

    No Known Activations