© 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. 110678
    Prev
    Next
    INDEX
    Explanations

    high-quality speaker

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

    The neuron strongly activates on numeric specification values—especially decimal measurements—within product descriptions.

    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
    ּוֹ
    -1.80
    ֶּ
    -1.77
     Enquanto
    -1.77
     Informações
    -1.77
     великолеп
    -1.68
    のおかげ
    -1.66
     Início
    -1.63
     Muitos
    -1.61
    Então
    -1.60
     лікар
    -1.60
    POSITIVE LOGITS
     your
    2.52
     sánh
    1.75
     is
    1.71
     our
    1.66
     also
    1.54
    acara
    1.54
     XVII
    1.54
    ׇ
    1.54
    '];
    1.51
     you
    1.48
    Activations Density 0.084%

    No Known Activations