© 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. 65261
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions or questions

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

    The neuron responds to common German function words (articles, prepositions, and conjunctions).

    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
     them
    -1.77
    
    -1.63
     rése
    -1.54
    僰
    -1.52
     étanche
    -1.50
     but
    -1.42
    archiwizowane
    -1.38
    roslav
    -1.36
     tém
    -1.35
     pozwala
    -1.34
    POSITIVE LOGITS
     by
    2.38
     oleh
    1.41
    like
    1.40
     kommen
    1.39
     ”
    1.35
    oules
    1.33
     menengah
    1.30
    Географија
    1.29
    1.29
         
    1.29
    Activations Density 0.002%

    No Known Activations