© 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. 84012
    Prev
    Next
    INDEX
    Explanations

    Jewish and Christian relations

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

    The neuron strongly activates on numeric tokens—especially verse numbers, statistics, and other standalone numerals.

    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
     each
    -0.85
     russian
    -0.85
     sociedade
    -0.84
    鞏
    -0.82
     spanish
    -0.81
    zło
    -0.79
    زندگی
    -0.79
    譴
    -0.78
     instalado
    -0.78
     texas
    -0.77
    POSITIVE LOGITS
     grafted
    1.22
     grafting
    1.07
     genti
    0.99
     Gentiles
    0.93
     Gentile
    0.92
     fulfilment
    0.89
     العن
    0.88
    Ἰ
    0.87
     racially
    0.87
     blindness
    0.86
    Activations Density 0.009%

    No Known Activations