© 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. 34-GEMMASCOPE-RES-131K
    7. 62850
    Prev
    Next
    INDEX
    Explanations

    Marine Corps

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

    The neuron strongly activates on mentions of the U.S. Marine Corps (e.g. “Marine,” “Corps,” “Boot Camp,” 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_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
    tellations
    -0.77
     monop
    -0.73
     كأس
    -0.71
    の方に
    -0.71
     Nullable
    -0.71
    itica
    -0.69
     CCI
    -0.69
    ansa
    -0.68
    cyon
    -0.67
     къ
    -0.66
    POSITIVE LOGITS
     Marine
    2.59
     Marines
    2.56
    Marine
    2.42
     marines
    2.31
     marine
    2.09
    marine
    1.88
     MARINE
    1.81
    marines
    1.64
     Corps
    1.20
     Toys
    1.03
    Activations Density 0.018%

    No Known Activations