© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15665
    Prev
    Next
    INDEX
    Explanations

    citations and academic references

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

    The neuron detects the closing tokens of inline reference citations (e.g. “]”, “\]”, “).”).

    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
     \
    -1.79
     It
    -1.56
     will
    -1.48
     By
    -1.45
     A
    -1.45
     If
    -1.44
     of
    -1.39
     This
    -1.34
     use
    -1.30
     '
    -1.27
    POSITIVE LOGITS
    푆
    1.43
    𝒴
    1.42
    骠
    1.27
     ľudí
    1.24
     クリア
    1.23
     ücret
    1.23
     untill
    1.23
     美しい
    1.22
    끫
    1.22
    的价格
    1.20
    Activations Density 0.037%

    No Known Activations