© 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. 34-GEMMASCOPE-RES-131K
    7. 59097
    Prev
    Next
    INDEX
    Explanations

    names and specific markers

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

    The neuron activates on the word “reaction” (as in “reaction time”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    襖
    -0.86
    諳
    -0.85
    keyColumn
    -0.82
     akibat
    -0.77
    ím
    -0.75
     آن‌ها
    -0.75
    FieldError
    -0.74
    และ
    -0.74
    AGO
    -0.73
     quelconque
    -0.73
    POSITIVE LOGITS
     Devlin
    0.82
    每個
    0.82
     systematic
    0.82
     carica
    0.81
     демон
    0.80
    Eller
    0.79
     modestly
    0.78
    vige
    0.77
    oding
    0.76
    ських
    0.76
    Activations Density 0.000%

    No Known Activations