© 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. 80822
    Prev
    Next
    INDEX
    Explanations

    war graves, cemeteries, memorials

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

    The neuron is keyed to names and phrases referring to formal war‐related burial or memorial institutions (e.g. Graves Commission, War Memorial, National Cemetery).

    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
     Advancement
    -0.78
    migiano
    -0.73
     Industry
    -0.73
     costumes
    -0.73
    sieh
    -0.71
     Happiness
    -0.70
     puertas
    -0.69
    日発売
    -0.69
    副本
    -0.68
    ائدة
    -0.68
    POSITIVE LOGITS
     grave
    1.05
     Grave
    0.97
     graves
    0.94
    Memorials
    0.89
    GRAV
    0.85
     cemeteries
    0.84
     GRAV
    0.81
    graves
    0.81
     cemetery
    0.81
     CW
    0.80
    Activations Density 0.030%

    No Known Activations