© 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. 41246
    Prev
    Next
    INDEX
    Explanations

    preferred followed by nouns

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

    This neuron detects occurrences of the word “preferred” (in any context or casing).

    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
    {
    -2.55
    擄
    -2.25
    籥
    -2.23
     privé
    -2.20
     стал
    -2.19
     представители
    -2.16
    鼉
    -2.16
    癰
    -2.14
    デュー
    -2.14
     fáciles
    -2.14
    POSITIVE LOGITS
    翾
    3.06
    酲
    2.64
    姈
    2.61
    鰾
    2.56
    淠
    2.52
    縲
    2.50
    摃
    2.47
    最后由
    2.38
    勍
    2.38
    ل
    2.33
    Activations Density 0.003%

    No Known Activations