© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103536
    Prev
    Next
    INDEX
    Explanations

    docket numbers

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

    The neuron strongly activates on legal citation numbers (e.g. docket or volume numbers) rather than on words.

    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
    badlogic
    -1.98
    你在
    -1.94
    そして
    -1.94
     sanoo
    -1.89
     Gedanke
    -1.89
    欉
    -1.88
     机械
    -1.84
    érape
    -1.84
    زيل
    -1.83
    と言って
    -1.77
    POSITIVE LOGITS
     is
    2.28
    ll
    2.19
    atguigu
    2.13
    那种
    2.11
    子を
    2.09
    釭
    2.09
     ambassador
    2.06
     occasione
    2.06
    ؟؟
    2.00
     embarazada
    2.00
    Activations Density 0.010%

    No Known Activations