© 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. 131042
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on high-frequency function words (e.g. articles, prepositions, and other common grammatical “stop” words).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    case or request

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     chré
    -1.76
    ׇ
    -1.54
     eccl
    -1.46
     chrétienne
    -1.34
     Dette
    -1.34
     musées
    -1.34
     možno
    -1.30
    CCIÓN
    -1.28
     "",
    -1.25
    ֩
    -1.23
    POSITIVE LOGITS
    ַּ
    2.02
    ֶּ
    1.73
    ּוֹ
    1.68
    ִּ
    1.58
     decision
    1.52
    וּ
    1.52
     request
    1.50
    ֵּ
    1.48
     that
    1.46
     submitted
    1.44
    Activations Density 0.042%

    No Known Activations