© 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. 8677
    Prev
    Next
    INDEX
    Explanations

    names of people, places, and organizations

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

    The neuron activates on capitalized proper nouns—especially names of places, institutions, and organizations.

    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
     who
    -1.77
     also
    -1.72
    Also
    -1.55
    It
    -1.37
    EDING
    -1.27
    ชอบ
    -1.26
     ALSO
    -1.24
    ৄ
    -1.24
    MediaStore
    -1.24
    ínguez
    -1.23
    POSITIVE LOGITS
     maisons
    1.38
     auteurs
    1.30
     tempel
    1.30
     pajero
    1.29
     volkswagen
    1.28
     palio
    1.27
     sog
    1.24
     Realt
    1.23
     unſ
    1.23
     publie
    1.22
    Activations Density 0.226%

    No Known Activations