© 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. 68160
    Prev
    Next
    INDEX
    Explanations

    knowledge and its implications

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

    The neuron fires on words and phrases expressing knowledge, understanding, or discovery (e.g. “knowing,” “understanding,” “knowledge,” “vitamins” in the context of being “known” or “meant”).

    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
     parámetros
    -0.98
    ztus
    -0.91
    läs
    -0.90
     OUTPUT
    -0.90
    typical
    -0.89
    nuovo
    -0.88
    tenis
    -0.88
     angek
    -0.88
     измер
    -0.85
    Testi
    -0.85
    POSITIVE LOGITS
     knowledge
    2.69
     know
    2.11
    knowledge
    1.64
     Knowledge
    1.63
    Knowledge
    1.57
     understanding
    1.48
     conhecimento
    1.39
     knowing
    1.38
    知識
    1.35
     Knowing
    1.35
    Activations Density 0.092%

    No Known Activations