© 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. 22-GEMMASCOPE-RES-131K
    7. 129619
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on capitalized proper nouns—names of people, places, organizations, and other named entities.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    place names and proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     is
    -0.98
     here
    -0.93
    を作り
    -0.91
     hierfür
    -0.91
     vielleicht
    -0.88
     Ihren
    -0.85
    3
    -0.84
    9
    -0.84
     cooperación
    -0.83
     kênh
    -0.82
    POSITIVE LOGITS
     itself
    1.38
     stesso
    1.32
    uded
    1.28
    itself
    1.25
     itse
    1.24
     öf
    1.20
    haviours
    1.11
    ͞
    1.11
    yship
    1.09
    erdings
    1.09
    Activations Density 0.156%

    No Known Activations