© 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. 11459
    Prev
    Next
    INDEX
    Explanations

    magenta, Mets

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

    The neuron is triggered by occurrences of the color name “magenta.”

    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
    ve
    -3.06
    h
    -2.78
    j
    -2.73
    z
    -2.69
    u
    -2.58
    n
    -2.56
    x
    -2.55
    te
    -2.47
    ka
    -2.45
    ta
    -2.38
    POSITIVE LOGITS
    蚴
    2.47
    谵
    2.42
    ～。
    2.34
     colorida
    2.34
    ſſen
    2.30
    个
    2.27
    ｗｗ
    2.23
    …！
    2.22
    椟
    2.20
    醅
    2.19
    Activations Density 0.002%

    No Known Activations