© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65564
    Prev
    Next
    INDEX
    Explanations

    words ending in sk

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

    The neuron fires on tokens containing the letter sequence “sk” (as in “Saskia,” “Waskow,” “Niskayuna,” etc.).

    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
     seguente
    -0.74
    갇
    -0.74
    ጽ
    -0.73
    swan
    -0.70
    有什么
    -0.70
     gestartet
    -0.69
    יותר
    -0.69
    ческую
    -0.69
     dictators
    -0.69
    прочем
    -0.68
    POSITIVE LOGITS
     sk
    1.09
     Sk
    0.85
    тника
    0.81
    usiai
    0.78
     difícil
    0.78
     aż
    0.78
     نوز
    0.77
     duy
    0.76
    外部链接
    0.76
     ска
    0.75
    Activations Density 0.028%

    No Known Activations