© 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. 102467
    Prev
    Next
    INDEX
    Explanations

    military bases

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects numerical designators (and their surrounding unit/organization context) in military unit names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     ciencias
    -0.82
    льні
    -0.76
     comprensión
    -0.75
     differentiable
    -0.75
    didSet
    -0.74
     چهره
    -0.73
    åne
    -0.73
    (___
    -0.71
     ജ
    -0.71
     nhóm
    -0.69
    POSITIVE LOGITS
     bases
    1.70
     base
    1.66
     Base
    1.48
    bases
    1.41
     Naval
    1.34
     installations
    1.28
    base
    1.26
     Air
    1.23
     naval
    1.22
     Bases
    1.21
    Activations Density 0.059%

    No Known Activations