© 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. 22-GEMMASCOPE-RES-131K
    7. 68890
    Prev
    Next
    INDEX
    Explanations

    biblical quotes and phrases

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

    The neuron is keyed to modal and auxiliary verbs—especially “will,” “must,” and “shall”—marking predictive or prescriptive statements (as in scripture quotations).

    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
    퐿
    -1.36
     wohnung
    -1.33
     appeler
    -1.30
    🐽
    -1.23
     manchen
    -1.20
     bezahlt
    -1.19
    ַּ
    -1.19
    ּוֹ
    -1.19
     unange
    -1.18
     vacunas
    -1.18
    POSITIVE LOGITS
     in
    1.83
     which
    1.55
     clases
    1.27
     चीज़
    1.26
     had
    1.23
     (
    1.21
    龶
    1.19
     initWithFrame
    1.18
    🤯
    1.16
     [
    1.15
    Activations Density 0.012%

    No Known Activations