© 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. 47899
    Prev
    Next
    INDEX
    Explanations

    Copyright notices and licenses

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

    The neuron detects long, all-caps tokens typically found in file headers or license/meta sections (e.g. COPYRIGHT, PROCUREMENT, DONATE, TITLE).

    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
     EDITION
    -0.80
     persevere
    -0.73
     take
    -0.73
     takes
    -0.70
     taking
    -0.68
     santiago
    -0.68
     edición
    -0.68
     directly
    -0.68
     unplug
    -0.67
     allegedly
    -0.66
    POSITIVE LOGITS
    wner
    0.75
     Mehta
    0.74
    pshot
    0.68
    phard
    0.67
    龌
    0.66
    trends
    0.65
    
    0.65
     Vargas
    0.64
    ärme
    0.63
    ACTIV
    0.63
    Activations Density 0.082%

    No Known Activations