© 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. 83921
    Prev
    Next
    INDEX
    Explanations

    military ranks and units

    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
     milhões
    -0.80
     Broadcast
    -0.77
    Carrier
    -0.77
    carrier
    -0.74
    Rhône
    -0.73
    atula
    -0.73
     vlož
    -0.73
     abound
    -0.71
    cella
    -0.71
     tanong
    -0.70
    POSITIVE LOGITS
     regiments
    1.13
     regiment
    1.02
     powder
    0.90
    reg
    0.89
    recruit
    0.88
     colonel
    0.87
     Lohan
    0.82
     reg
    0.82
     Lodi
    0.81
     officer
    0.80
    Activations Density 0.039%

    No Known Activations