© 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. 31266
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical terms

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

    This neuron strongly activates on passages that are direct quotations of Christian scripture, especially the lamenting lines addressed to God (e.g. “My God, my God, why have you forsaken me?”).

    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
     Without
    -0.77
     without
    -0.76
    Without
    -0.74
    Although
    -0.72
     chồng
    -0.71
     mostrado
    -0.69
     wiadomo
    -0.69
     eszköz
    -0.68
    Commissioner
    -0.68
     Although
    -0.68
    POSITIVE LOGITS
     سرب
    0.86
     manus
    0.83
    ampi
    0.81
     Checklist
    0.81
     kịch
    0.80
    pageX
    0.79
     RISERVATA
    0.77
     quota
    0.77
    ListItem
    0.77
    ources
    0.76
    Activations Density 0.008%

    No Known Activations