© 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. 103630
    Prev
    Next
    INDEX
    Explanations

    software and code headers

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

    The neuron specializes in spotting license- and legal-disclaimer terms (e.g. “License,” “law,” “warranties,” “conditions”) in file headers.

    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
     Bucure
    -0.77
    CRON
    -0.74
    чайно
    -0.71
     menghilangkan
    -0.71
     daban
    -0.70
     mengal
    -0.70
     portail
    -0.69
     купа
    -0.69
    éra
    -0.69
    场上
    -0.69
    POSITIVE LOGITS
    לוס
    0.86
     necesarios
    0.82
     discus
    0.81
    ルター
    0.81
     Hira
    0.81
    ^{(\
    0.81
    irect
    0.79
     deva
    0.79
    inek
    0.78
    BACA
    0.78
    Activations Density 0.002%

    No Known Activations