© 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. 54247
    Prev
    Next
    INDEX
    Explanations

    legal citations and case numbers

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

    The neuron detects the numeric page‐reference (the specific page numbers) in legal reporter 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_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
     into
    -0.99
    许久
    -0.94
    Preferences
    -0.92
    nytimes
    -0.91
    を行い
    -0.90
     like
    -0.87
    Exception
    -0.86
    venidos
    -0.85
    Preference
    -0.84
    کتر
    -0.84
    POSITIVE LOGITS
     Bedienung
    1.29
     nordrhein
    1.05
    ftet
    1.01
    Всем
    0.98
    時間は
    0.98
     nutshell
    0.97
     навіть
    0.97
    Iden
    0.96
     قدیمی
    0.96
     württemberg
    0.96
    Activations Density 0.077%

    No Known Activations