© 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. 10-GEMMASCOPE-RES-131K
    7. 57617
    Prev
    Next
    INDEX
    Explanations

    president Bashar al-Assad

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

    The neuron activates on personal names (proper nouns identifying people).

    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
    媖
    -1.74
    极其
    -1.71
    another
    -1.58
     otras
    -1.55
    不可思议
    -1.52
     autre
    -1.50
    涠
    -1.49
     wiedzieć
    -1.48
     patrie
    -1.46
    愜
    -1.46
    POSITIVE LOGITS
     that
    2.97
     of
    2.25
     to
    1.71
     which
    1.64
     already
    1.48
     until
    1.45
     vandens
    1.44
     who
    1.43
     it
    1.37
     jų
    1.37
    Activations Density 0.068%

    No Known Activations