© 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. 40931
    Prev
    Next
    INDEX
    Explanations

    Zurich/Zürich and specific names

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

    The neuron activates strongly on mentions of the Swiss city “Zurich” (including “Zürich”).

    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
    es
    -2.86
     they
    -2.73
    퐿
    -2.72
    䊏
    -2.47
    訁
    -2.42
     enigmatic
    -2.39
    柺
    -2.36
    ન્
    -2.34
    檍
    -2.33
    section
    -2.27
    POSITIVE LOGITS
    .
    3.41
    </td>
    2.27
     They
    2.16
     We
    2.16
    逦
    2.14
     Trying
    2.08
     Only
    1.98
    攫
    1.94
     Those
    1.94
     And
    1.94
    Activations Density 0.001%

    No Known Activations