© 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. 61455
    Prev
    Next
    INDEX
    Explanations

    разные типы объектов

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

    This neuron detects Russian words in their plural inflected forms (i.e. nouns or adjectives ending in typical Russian plural suffixes).

    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
    ed
    -3.09
     was
    -3.00
    er
    -2.86
    {
    -2.73
    al
    -2.66
    们的
    -2.66
    it
    -2.58
    en
    -2.58
    es
    -2.56
    的
    -2.52
    POSITIVE LOGITS
     közül
    2.81
    盦
    2.72
    嘡
    2.56
    賔
    2.47
     بسیار
    2.39
    轵
    2.38
    
    2.31
    ܊
    2.25
    歆
    2.22
    fél
    2.20
    Activations Density 0.002%

    No Known Activations