© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90419
    Prev
    Next
    INDEX
    Explanations

    military ranks and enlisted personnel

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

    This neuron is detecting mentions of military ranks and rank-related titles (e.g., “Sergeant,” “Chief of Staff,” “NCOIC,” “Lieutenant Colonel,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    i
    -1.59
     conceded
    -1.44
    改为
    -1.32
    $
    -1.30
    ワンピース
    -1.30
    ill
    -1.27
     некото
    -1.27
    <
    -1.26
    	
    -1.25
    ....
    -1.23
    POSITIVE LOGITS
    `,
    
    1.51
    Ꭳ
    1.41
    [])
    
    1.41
    >");
    
    1.39
     edisi
    1.35
    
    1.35
    ()]);
    1.34
    QPushButton
    1.34
     Dimensiones
    1.33
    лит
    1.32
    Activations Density 0.018%

    No Known Activations