© 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. 22-GEMMASCOPE-RES-131K
    7. 16395
    Prev
    Next
    INDEX
    Explanations

    элемента списка

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

    The neuron fires on Cyrillic-script content words (i.e. Russian words, especially nouns).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    It
    -2.16
    end
    -1.73
    {
    -1.68
    He
    -1.61
     it
    -1.52
     beinahe
    -1.52
    th
    -1.47
    了下
    -1.44
     pomiędzy
    -1.43
     this
    -1.42
    POSITIVE LOGITS
     horrors
    1.73
    quelles
    1.70
    warzys
    1.70
    henswürdigkeiten
    1.69
     ícones
    1.65
    ÈNE
    1.62
    鮰
    1.59
    ]');
    1.55
    🫅
    1.54
    癀
    1.53
    Activations Density 0.016%

    No Known Activations