© 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. 34-GEMMASCOPE-RES-131K
    7. 107881
    Prev
    Next
    INDEX
    Explanations

    legal case citations

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

    The neuron flags the bibliographic markers of formal legal citations—i.e. the volume numbers and court‐reporter abbreviations (the all-caps letters and numerals that occur in case 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_34/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
     still
    -1.19
     had
    -1.13
    S
    -1.09
    A
    -1.08
    e
    -1.08
     often
    -1.07
    R
    -1.05
     mainly
    -1.03
     manages
    -1.02
    M
    -1.02
    POSITIVE LOGITS
    甗
    1.30
    Université
    1.29
    Daha
    1.27
    킁
    1.23
     pokoj
    1.23
    ܆
    1.21
     différentes
    1.20
     kontro
    1.20
     relâche
    1.18
    iTunes
    1.16
    Activations Density 0.205%

    No Known Activations