© 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. 10-GEMMASCOPE-RES-131K
    7. 72802
    Prev
    Next
    INDEX
    Explanations

    page numbers and references

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

    The neuron flags numeric page‐reference tokens (e.g. the page counts or page‐range numbers in bibliographic entries).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    肏
    -3.11
    妧
    -2.86
    ︕
    -2.75
    鸱
    -2.63
     哪些
    -2.44
    到处
    -2.36
    鲧
    -2.36
    \
    -2.34
     techni
    -2.33
    みたいに
    -2.33
    POSITIVE LOGITS
     pages
    2.67
    d
    2.30
     intricacies
    2.28
    х
    2.27
     zuneh
    2.23
     Ironically
    2.22
     ganze
    2.22
    𐐪
    2.20
     Surprisingly
    2.19
     nuanced
    2.13
    Activations Density 0.009%

    No Known Activations