© 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. 67199
    Prev
    Next
    INDEX
    Explanations

    citations and legal cases

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

    This neuron activates on long multi‐digit numeric tokens (e.g. page numbers, years, or volume/reference identifiers) typically found in citations and 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
    嘞
    -2.03
    、“
    -1.75
     categorized
    -1.66
    ～。
    -1.58
     another
    -1.58
     attempting
    -1.55
     completing
    -1.52
     skuto
    -1.52
     having
    -1.46
     zvyš
    -1.46
    POSITIVE LOGITS
    They
    1.68
     Either
    1.62
    朝着
    1.55
     согласно
    1.50
    镡
    1.49
    ⎔
    1.48
    ㉗
    1.48
     такую
    1.46
    
    1.46
     irres
    1.45
    Activations Density 0.095%

    No Known Activations