© 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. 42878
    Prev
    Next
    INDEX
    Explanations

    German Proper Nouns

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

    The neuron is responding to tokens that are capitalized names or proper nouns (e.g. people, places, brands, organizations).

    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
    </u>
    -1.77
       
    -1.55
              
    -1.51
    ↵
    -1.48
               
    -1.47
        
    -1.46
     You
    -1.41
             
    -1.40
    </strong>
    -1.38
    "},
    -1.34
    POSITIVE LOGITS
     mengha
    1.45
     žá
    1.42
     selección
    1.30
    總結
    1.30
     menyebutkan
    1.29
    棪
    1.28
    ỏng
    1.28
    Мето
    1.27
    1
    1.27
     partenaire
    1.25
    Activations Density 0.988%

    No Known Activations