© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15009
    Prev
    Next
    INDEX
    Explanations

    religious or technical contexts

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

    The neuron fires on explicit expressions of religious faith or devotion (e.g. “believe in Jesus,” “step of faith,” “fasting … from sin,” “rely on God,” “remain committed”).

    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
    Informationen
    -1.23
    providing
    -1.18
     verschillende
    -1.17
    这一幕
    -1.16
    álise
    -1.14
     if
    -1.14
    וּ
    -1.14
    nearly
    -1.13
     referrerpolicy
    -1.12
    却被
    -1.11
    POSITIVE LOGITS
    athons
    1.19
     τὴν
    1.19
    =?";
    1.15
    踵
    1.12
    💞
    1.11
     anglès
    1.09
     asks
    1.08
    漣
    1.07
    🤪
    1.07
     daily
    1.07
    Activations Density 0.013%

    No Known Activations