© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40655
    Prev
    Next
    INDEX
    Explanations

    questions starting with "do you know"

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

    The neuron primarily activates on the word “know,” especially when it appears in questions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    \
    -1.94
    '
    -1.71
    year
    -1.52
    ches
    -1.51
    ri
    -1.44
    n
    -1.44
    to
    -1.42
    f
    -1.38
    }
    -1.38
    like
    -1.34
    POSITIVE LOGITS
     Acesso
    1.71
     particolar
    1.60
     کافی
    1.55
    ;;)
    1.52
    是怎么回事
    1.51
     metav
    1.49
     kao
    1.45
     umożli
    1.43
     ajud
    1.41
     Dados
    1.41
    Activations Density 0.017%

    No Known Activations