© 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. 130689
    Prev
    Next
    INDEX
    Explanations

    This neuron strongly activates on author surnames in academic‐style citations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    苕
    -1.16
     Pumpkin
    -1.16
    ܜ
    -1.13
     חיצוני
    -1.13
     durer
    -1.13
     pantaloni
    -1.10
    Faktor
    -1.09
    பி
    -1.09
     molta
    -1.09
    たまた
    -1.08
    POSITIVE LOGITS
     with
    1.30
     often
    1.19
    などを
    1.15
    と
    1.02
    などの
    1.02
    ,
    0.98
    l
    0.96
     "
    0.94
    and
    0.92
    や
    0.91
    Activations Density 0.001%

    No Known Activations