© 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. 111882
    Prev
    Next
    INDEX
    Explanations

    пикча, python, массив

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

    Cyrillic characters, particularly in Russian text on Stack Overflow programming questions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects Cyrillic-script character sequences (i.e. Russian text segments).

    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
     a
    -2.80
    踅
    -2.67
    摃
    -2.64
    which
    -2.59
     которые
    -2.56
    谖
    -2.55
    THEY
    -2.55
    時間も
    -2.52
     可愛い
    -2.44
    CHREIB
    -2.39
    POSITIVE LOGITS
     has
    2.69
     Despite
    2.66
     three
    2.56
     newly
    2.53
     and
    2.50
     after
    2.48
     meticulous
    2.45
     Kälte
    2.45
     remarkable
    2.45
     eight
    2.45
    Activations Density 0.006%

    No Known Activations