© 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. 43023
    Prev
    Next
    INDEX
    Explanations

    Switzerland and following punctuation

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

    The neuron activates on occurrences of the country name “Switzerland.”

    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
    2
    -3.05
    or
    -2.73
    7
    -2.59
    9
    -2.48
    是
    -2.45
    其他
    -2.45
    樒
    -2.45
    4
    -2.41
    8
    -2.34
    u
    -2.33
    POSITIVE LOGITS
    ⟞
    2.73
    酝
    2.70
    怍
    2.64
    镚
    2.52
    髏
    2.48
    锜
    2.47
    ጧ
    2.39
    ᠁
    2.39
    .
    2.38
    钿
    2.38
    Activations Density 0.001%

    No Known Activations