© 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. 10-GEMMASCOPE-RES-131K
    7. 128899
    Prev
    Next
    INDEX
    Explanations

    journal article citations

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

    The neuron activates on numeric tokens—especially four‐digit numbers representing publication years in reference citations.

    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
    着一个
    -1.93
     AMAZING
    -1.85
     juſt
    -1.68
     Dinas
    -1.67
    ったのは
    -1.66
     germain
    -1.65
    着自己的
    -1.62
     Vám
    -1.60
    commonly
    -1.59
     密码
    -1.59
    POSITIVE LOGITS
     more
    2.84
     many
    2.48
     most
    2.28
    .
    2.20
     both
    2.06
     with
    2.05
     не
    2.02
     several
    2.00
     only
    1.98
     all
    1.93
    Activations Density 0.074%

    No Known Activations