© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72727
    Prev
    Next
    INDEX
    Explanations

    prints and patterns

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

    The neuron is especially responsive to words denoting printed patterns or fabric prints (e.g., “print,” “pattern,” “floral,” “plaid,” “embroidery”).

    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
     イベント
    -1.39
    掸
    -1.37
     visualizar
    -1.37
    に於
    -1.32
     atualizado
    -1.30
     frança
    -1.29
    敺
    -1.28
     him
    -1.27
    んご
    -1.26
    erobic
    -1.25
    POSITIVE LOGITS
     enkel
    1.24
     și
    1.24
     και
    1.23
    しました
    1.23
     öv
    1.23
    ла
    1.23
    美女
    1.21
     udało
    1.18
     \&
    1.16
     aantal
    1.15
    Activations Density 0.019%

    No Known Activations