© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71568
    Prev
    Next
    INDEX
    Explanations

    Christian liturgy and sacraments

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

    The neuron strongly activates on text about the handling, transport, and use of Catholic “holy water.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     didn
    -1.62
    ૉ
    -1.59
     فره
    -1.28
     parlement
    -1.27
     głównie
    -1.23
     描
    -1.21
     paillettes
    -1.20
    ⍳
    -1.16
     agradable
    -1.16
    TableRow
    -1.16
    POSITIVE LOGITS
    Beskrivelse
    1.35
    暧
    1.32
     his
    1.24
     évêque
    1.19
    ῾
    1.17
     sogar
    1.16
     rightly
    1.16
    omalies
    1.13
    Appellants
    1.13
    ysql
    1.12
    Activations Density 0.046%

    No Known Activations