© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20561
    Prev
    Next
    INDEX
    Explanations

    state abbreviations in legal citations

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

    The main thing this neuron does is identify and highlight legal case‐citation reporter abbreviations and volumes (e.g., “Ga.,” “App.,” “P.,” etc.).

    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
    珦
    -1.95
    CHREIB
    -1.68
    ortiment
    -1.64
    machten
    -1.63
     ἡ
    -1.54
    boBox
    -1.50
     ὁ
    -1.49
     muchos
    -1.48
    KommentareTeilen
    -1.46
     klass
    -1.46
    POSITIVE LOGITS
    in
    1.70
     that
    1.63
    "
    1.55
    or
    1.53
     warmen
    1.38
    ness
    1.38
     where
    1.37
    er
    1.35
    an
    1.32
     were
    1.32
    Activations Density 0.071%

    No Known Activations