© 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. 22-GEMMASCOPE-RES-131K
    7. 73869
    Prev
    Next
    INDEX
    Explanations

    manuscript or manuscripts

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

    The neuron activates on occurrences of the word “manuscript.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    鼉
    -2.52
     positifs
    -2.39
     définiti
    -2.30
     ſever
    -2.28
     gesagt
    -2.17
     occidentale
    -2.17
    美
    -2.14
     unſ
    -2.09
    ркут
    -2.02
     voglio
    -2.00
    POSITIVE LOGITS
    ↵
    3.23
    最后由
    2.38
    总之
    2.27
     noteworthy
    2.25
    酒屋
    2.13
    
    2.11
     slight
    2.09
    衕
    2.08
    ITERIA
    2.03
    以上就是
    2.00
    Activations Density 0.007%

    No Known Activations