© 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. 98605
    Prev
    Next
    INDEX
    Explanations

    incorporating or including elements

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

    The neuron triggers on longer, multi-syllable, domain-specific content nouns (e.g. “uncertainty,” “research,” “pikes”).

    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
     oído
    -1.29
     käytet
    -1.18
     siitä
    -1.14
     sellado
    -1.10
     passés
    -1.03
     costuras
    -1.01
     muualla
    -1.01
     mejoras
    -0.99
     fermée
    -0.99
     réellement
    -0.98
    POSITIVE LOGITS
     into
    2.63
     to
    2.59
     in
    2.39
     as
    1.91
     onto
    1.41
     on
    1.34
     among
    1.21
    เข้า
    1.19
    ในการ
    1.18
     included
    1.17
    Activations Density 0.092%

    No Known Activations