© 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. 22-GEMMASCOPE-RES-131K
    4. 70630
    Prev
    Next
    INDEX
    Explanations

    legal citations abbreviations

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

    The neuron is detecting segments of legal case citations, such as bracketed report years, volume numbers, and reporter abbreviations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    legal case citations and reporter references in court documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     you
    -1.20
    ようですが
    -1.20
     vitara
    -1.20
    為に
    -1.17
    同样
    -1.15
     utaf
    -1.12
    様に
    -1.10
    eleste
    -1.07
     cabrio
    -1.06
     οὐ
    -1.06
    POSITIVE LOGITS
    دانلود
    1.39
    donde
    1.36
     proteína
    1.35
    Szer
    1.29
    狡
    1.24
    brtc
    1.23
    Hogyan
    1.20
    がありますが
    1.18
     mencegah
    1.16
     précédent
    1.16
    Activations Density 0.034%

    No Known Activations