© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 80598
    Prev
    Next
    INDEX
    Explanations

    know what, know who, know how

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

    The neuron activates on occurrences of the verb “know.”

    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
    вгений
    -1.99
     transférez
    -1.98
     notwendigen
    -1.97
     deafening
    -1.96
     genannten
    -1.91
    要不然
    -1.91
     jarring
    -1.88
    オリン
    -1.88
    當然
    -1.84
    デュー
    -1.82
    POSITIVE LOGITS
     about
    2.14
     and
    1.95
     with
    1.73
     what
    1.72
     começaram
    1.65
     before
    1.61
     whose
    1.61
     when
    1.61
    玧
    1.60
     terv
    1.59
    Activations Density 0.024%

    No Known Activations