© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108252
    Prev
    Next
    INDEX
    Explanations

    document page references

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

    The neuron detects bibliographic reference markers—numbers and terms that identify book titles, editions, pages, and similar citation metadata.

    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
    えっ
    -0.88
     مقالات
    -0.87
     ソファ
    -0.85
    äus
    -0.84
     étant
    -0.84
    
    -0.83
    erdere
    -0.83
     acuer
    -0.82
     یک
    -0.81
    рованы
    -0.81
    POSITIVE LOGITS
     page
    3.97
     pages
    3.19
    page
    2.77
     Page
    2.73
    Page
    2.63
     pg
    2.33
     página
    2.14
    pages
    1.98
     Pages
    1.97
     paragraph
    1.94
    Activations Density 0.104%

    No Known Activations