© 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. 70513
    Prev
    Next
    INDEX
    Explanations

    knit and knitting

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

    The neuron detects occurrences of the word “knit” (and its inflected forms like “knitting,” “knitted”) in the text.

    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
    秝
    -2.56
    鸰
    -2.44
    苼
    -2.39
    ad
    -2.38
    鲀
    -2.36
    嫆
    -2.33
    Приложение
    -2.30
    ik
    -2.28
    Ⲉ
    -2.23
    鱻
    -2.19
    POSITIVE LOGITS
    >
    3.22
     organisiert
    2.41
    }\
    2.31
    кой
    2.31
    We
    2.27
    1
    2.22
     های
    2.20
     You
    2.20
    ль
    2.09
    ра
    2.08
    Activations Density 0.004%

    No Known Activations