© 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. 38577
    Prev
    Next
    INDEX
    Explanations

    pronouns and determiners

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

    The neuron fires on Russian words bearing inflectional case endings (e.g. genitive “-его/–ей” or prepositional “–нём”), detecting Cyrillic suffixes that mark case.

    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
     of
    -2.36
    蛩
    -2.22
    瑧
    -2.14
    fordshire
    -2.11
    ၟ
    -2.08
    古风
    -2.06
     酥
    -2.06
     可爱
    -2.03
    𓐍
    -2.02
    玙
    -1.97
    POSITIVE LOGITS
     It
    3.44
     ‘’
    2.77
     The
    2.27
    </h1>
    2.16
     ANOTHER
    2.05
     ‘‘
    1.99
    ’
    1.92
     ''
    1.91
    la
    1.89
     ”
    1.88
    Activations Density 0.003%

    No Known Activations