© 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. 22-GEMMASCOPE-RES-131K
    7. 35523
    Prev
    Next
    INDEX
    Explanations

    court case numbers and dates

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

    The neuron consistently lights up on standalone numeric tokens (especially single‐digit numbers) used in legal documents for dates, docket numbers, and 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
     hornear
    -1.03
     joueurs
    -0.98
    cheese
    -0.98
     éton
    -0.94
     burbujas
    -0.94
     pistolet
    -0.94
    Literacy
    -0.94
     fréquent
    -0.94
     passagers
    -0.93
    僳
    -0.93
    POSITIVE LOGITS
     more
    1.22
     although
    1.17
     even
    1.12
     to
    1.09
     had
    1.05
     from
    1.05
    An
    1.00
    You
    1.00
     predomin
    0.99
     ultimately
    0.98
    Activations Density 0.138%

    No Known Activations