© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34086
    Prev
    Next
    INDEX
    Explanations

    veterans' health and affairs

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

    The neuron fires on mentions of veterans or the Veterans Affairs (VA) system.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     You
    -2.64
     `
    -2.17
    ]
    -2.13
     Besonder
    -2.09
     weiße
    -2.05
     wist
    -2.02
    1
    -2.00
     The
    -1.99
     serán
    -1.98
     {
    -1.97
    POSITIVE LOGITS
     复古
    2.59
    ؟
    2.50
    
    2.45
    ୌ
    2.38
    %?
    2.38
     kerana
    2.36
    ‪.‬‬
    2.33
     -->
    2.30
    If
    2.28
     水墨
    2.28
    Activations Density 0.006%

    No Known Activations