© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107577
    Prev
    Next
    INDEX
    Explanations

    legal filing introductions and technical terms

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

    The neuron activates on long, dot-delimited identifier sequences (e.g. code namespaces or fully qualified class/module names).

    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
    饰
    -0.76
     fame
    -0.74
     standar
    -0.73
     SDR
    -0.73
    ət
    -0.71
     chanteur
    -0.71
     Crucial
    -0.70
     segreg
    -0.69
    oley
    -0.68
    庄
    -0.67
    POSITIVE LOGITS
     device
    0.88
    uerta
    0.74
    among
    0.72
    kud
    0.72
    模糊
    0.70
    peted
    0.70
    阈
    0.70
     registration
    0.69
    жаться
    0.69
     devices
    0.68
    Activations Density 0.009%

    No Known Activations