© 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. 11329
    Prev
    Next
    INDEX
    Explanations

    Российский алгоритм

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

    The neuron fires on Russian nouns in their instrumental-case (–ом, –ами, –ением, etc.) forms.

    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
     unrelenting
    -2.80
     unparalleled
    -2.64
    錨
    -2.58
     frantic
    -2.52
     edgy
    -2.50
     nine
    -2.47
     ingrained
    -2.47
     ingenious
    -2.45
     or
    -2.44
    !!!!!
    -2.44
    POSITIVE LOGITS
     they
    2.92
     semelh
    2.89
    赑
    2.88
    鹇
    2.88
     decidedly
    2.80
    ౭
    2.73
     botão
    2.70
    several
    2.66
    卝
    2.66
    乄
    2.64
    Activations Density 0.008%

    No Known Activations