© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45642
    Prev
    Next
    INDEX
    Explanations

    der

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

    The neuron fires on occurrences of the German definite article “der” (including its capitalized form “Der”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    e
    -2.44
    镲
    -2.42
     trzech
    -2.42
    ⚣
    -2.30
    いって
    -2.23
    튿
    -2.23
     à
    -2.22
     celebrates
    -2.19
    ጴ
    -2.19
     hauptsächlich
    -2.13
    POSITIVE LOGITS
     Despite
    2.52
     Within
    2.52
     Although
    2.45
     There
    2.44
    ان
    2.36
     Unlike
    2.30
     What
    2.28
     mulia
    2.25
     Even
    2.23
    ﺐ
    2.23
    Activations Density 0.001%

    No Known Activations