© 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. 31050
    Prev
    Next
    INDEX
    Explanations

    burial and interment

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     cadrul
    -0.90
     geschaffen
    -0.86
    ทำงาน
    -0.85
     grooms
    -0.79
    umerate
    -0.79
     aufges
    -0.73
    恻
    -0.73
    beaten
    -0.72
    肃
    -0.72
     survivor
    -0.71
    POSITIVE LOGITS
     burial
    2.36
     interment
    2.17
     Burial
    2.02
     Interment
    2.02
    Interment
    1.91
    Burial
    1.67
     burying
    1.56
     buried
    1.55
     graves
    1.48
     burials
    1.46
    Activations Density 0.005%

    No Known Activations