© 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. 34483
    Prev
    Next
    INDEX
    Explanations

    telecom network sectorization

    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
     sĩ
    -0.71
    歼
    -0.71
     پرورش
    -0.70
    シ
    -0.70
    hd
    -0.68
    bahaya
    -0.67
     Nih
    -0.67
     aeros
    -0.66
    restaurant
    -0.66
     desarrollo
    -0.66
    POSITIVE LOGITS
     Ericsson
    0.87
     Sites
    0.85
    MSC
    0.82
     sites
    0.80
     Capacity
    0.80
    Sites
    0.79
    Aspen
    0.76
     stoppen
    0.76
     MSC
    0.75
    shortcode
    0.75
    Activations Density 0.061%

    No Known Activations