© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112128
    Prev
    Next
    INDEX
    Explanations

    flowers and Pelicans

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

    The neuron fires on names of ornamental plants and flowers.

    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
    紲
    -2.53
    ？）
    -2.33
    ឬ
    -2.25
    寕
    -2.25
    箩
    -2.23
    樒
    -2.22
    ’;
    -2.14
    ですから
    -2.13
    鲠
    -2.13
     impec
    -2.11
    POSITIVE LOGITS
    \\
    2.61
     "
    2.25
    2.19
    鋱
    2.19
     When
    2.06
    </h1>
    2.06
    🎉
    2.06
    a
    2.00
    `
    1.97
     любить
    1.95
    Activations Density 0.005%
    No Known Activations