© 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. 34966
    Prev
    Next
    INDEX
    Explanations

    infantry regiments and divisions

    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
     squadron
    -1.20
     squadrons
    -1.07
     Squadron
    -0.96
     anfitrión
    -0.82
    phyllum
    -0.79
     accessory
    -0.77
     ingeniero
    -0.76
     xinh
    -0.75
    アマ
    -0.71
     ridden
    -0.70
    POSITIVE LOGITS
     foot
    0.82
    玉
    0.76
    soldier
    0.73
    lepší
    0.73
     Quindi
    0.71
    Teléfono
    0.69
    碱
    0.69
     Foot
    0.67
     Amer
    0.67
    simon
    0.67
    Activations Density 0.040%

    No Known Activations