© 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. 43394
    Prev
    Next
    INDEX
    Explanations

    Danish origin

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

    The neuron detects references to Denmark, such as “Danish,” “Denmark,” or “Danske.”

    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
     ,"
    -2.66
     
    -2.58
    がこの
    -2.52
    十分的
    -2.50
     "
    -2.50
     อย่าง
    -2.48
    菹
    -2.36
     deberes
    -2.28
    を始め
    -2.25
    𐐀
    -2.23
    POSITIVE LOGITS
    </td>
    3.16
    It
    3.06
    In
    2.78
    1
    2.75
    I
    2.73
    >
    2.61
    A
    2.59
    </h5>
    2.58
    E
    2.53
    O
    2.48
    Activations Density 0.005%

    No Known Activations