© 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. 63900
    Prev
    Next
    INDEX
    Explanations

    biblical

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

    The neuron fires on etymology metadata in name‐entry contexts—phrases describing a given name’s language or cultural origin (e.g. “Hebrew origin,” “biblical figure,” 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
     chlor
    -0.87
    MAGIC
    -0.86
     calorie
    -0.80
    핑
    -0.79
    reloj
    -0.76
    היו
    -0.75
    picious
    -0.73
    溧
    -0.73
    ButterKnife
    -0.73
    ήσει
    -0.72
    POSITIVE LOGITS
     biblical
    4.34
     Biblical
    4.03
     Bible
    3.02
    Bib
    2.97
    bib
    2.88
     bib
    2.61
     bible
    2.44
     bibl
    2.39
     Bib
    2.30
    Bible
    2.22
    Activations Density 0.063%

    No Known Activations