© 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. 10-GEMMASCOPE-RES-131K
    7. 57646
    Prev
    Next
    INDEX
    Explanations

    German state and political terms

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

    The neuron strongly activates on long compound words—especially German-style concatenated nouns.

    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
     would
    -2.08
     
    -2.06
    ℣
    -2.00
     "
    -1.85
     was
    -1.84
    𝄆
    -1.81
    岀
    -1.72
     cuentan
    -1.69
     is
    -1.68
     porém
    -1.64
    POSITIVE LOGITS
    _
    2.08
    獁
    2.02
    Using
    2.00
    ’,
    2.00
    ’.
    1.97
    不要
    1.95
     福袋
    1.93
    Some
    1.91
    ,’
    1.90
    Surprisingly
    1.88
    Activations Density 0.019%

    No Known Activations