© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47661
    Prev
    Next
    INDEX
    Explanations

    Slavic surnames and words

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

    The neuron detects occurrences of the “zh” or “ž” character sequence used in Slavic or Eastern‐European names and terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ylene
    -0.74
    auti
    -0.71
     poroz
    -0.69
    Dialect
    -0.68
    тию
    -0.68
     there
    -0.68
     church
    -0.67
     WMA
    -0.67
     odst
    -0.67
    ibe
    -0.67
    POSITIVE LOGITS
    ׂ
    1.10
    ウィ
    0.81
    он
    0.77
    Gem
    0.75
    ор
    0.73
    джа
    0.73
    NW
    0.73
    Ener
    0.71
    ullan
    0.71
    itsu
    0.71
    Activations Density 0.011%

    No Known Activations