© 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. 111603
    Prev
    Next
    INDEX
    Explanations

    есть / is there / has

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

    This neuron detects occurrences of the Russian verb “есть” (the existential/copular “to be/there is”).

    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
    -3.36
    ,"
    -2.89
    是因為
    -2.73
    un
    -2.70
    o
    -2.58
    是個
    -2.53
    ו
    -2.50
    為何
    -2.47
    持續
    -2.38
    那时候
    -2.28
    POSITIVE LOGITS
     “
    2.63
    眨眼
    2.50
    目次
    2.47
    vantaged
    2.36
     schnelle
    2.31
    cadilly
    2.30
     potenci
    2.27
    を使用した
    2.23
    突破
    2.22
     trouble
    2.20
    Activations Density 0.001%

    No Known Activations