© 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. 34-GEMMASCOPE-RES-131K
    7. 92372
    Prev
    Next
    INDEX
    Explanations

    Swedish or Nordic place names

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

    The neuron is strongly activated by any token containing the letter sequence “ny” (e.g. “Nyasaland,” “Nybergsund,” “nytimes,” “NYCB,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Lymp
    -0.75
    ிய
    -0.75
    連
    -0.72
    dehydes
    -0.70
    最終
    -0.69
    ྣ
    -0.68
    وفق
    -0.68
    كور
    -0.68
    روج
    -0.68
     Ráp
    -0.68
    POSITIVE LOGITS
     боя
    0.81
     tendons
    0.79
     immedi
    0.76
    姝
    0.75
     ”.
    0.75
     Sanford
    0.72
     nya
    0.72
     Ny
    0.72
     shen
    0.72
     Certains
    0.71
    Activations Density 0.021%

    No Known Activations