© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62641
    Prev
    Next
    INDEX
    Explanations

    burial linens wraps

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

    This neuron flags mentions of the Shroud of Turin (and its context, e.g. linen, burial of Jesus, visits by the Pope).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     UNICEF
    -0.78
     antigens
    -0.74
     turbines
    -0.73
     спла
    -0.71
    ěr
    -0.69
    扁
    -0.69
    responseType
    -0.68
     ordinance
    -0.67
     induction
    -0.67
     as
    -0.67
    POSITIVE LOGITS
     tomb
    1.14
     burial
    0.99
     WRAP
    0.90
    tomb
    0.89
     spices
    0.88
    WRAP
    0.88
     linens
    0.85
     wrapper
    0.85
     sepul
    0.84
    SUPPORTED
    0.83
    Activations Density 0.007%

    No Known Activations