© 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. 60394
    Prev
    Next
    INDEX
    Explanations

    status, style, content, help

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

    The neuron fires on occurrences of HTML “class=” attribute values (i.e. tokens inside class="…").

    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
    ’
    -1.77
    すべき
    -1.56
     it
    -1.52
     you
    -1.39
    是因为
    -1.36
     has
    -1.31
    量は
    -1.30
     пунктов
    -1.25
    这也是
    -1.25
     которой
    -1.25
    POSITIVE LOGITS
    휀
    1.63
     originalen
    1.55
    gettyimages
    1.55
    鹮
    1.53
     gewiß
    1.52
     sicherzustellen
    1.52
     zustand
    1.48
    rdoba
    1.46
     grüne
    1.45
     traditionelle
    1.45
    Activations Density 0.006%

    No Known Activations