© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67129
    Prev
    Next
    INDEX
    Explanations

    appellant or appeal

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

    The neuron fires on the uppercase letter sequences and numbers that make up formal legal‐citation headings (e.g. docket numbers, court abbreviations, and party-designation terms in case captions).

    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
     ‘‘
    -1.46
    aguars
    -1.22
     («
    -1.21
    ϟ
    -1.18
    ↵↵↵↵↵↵↵↵↵↵↵
    -1.18
     utro
    -1.18
     ‘’
    -1.17
    lichte
    -1.16
     »,
    -1.16
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.16
    POSITIVE LOGITS
     zanim
    1.34
     almofada
    1.30
     начинается
    1.26
     Şubat
    1.21
     използва
    1.19
     udě
    1.18
     layar
    1.16
    颧
    1.15
     населення
    1.15
    erevan
    1.13
    Activations Density 0.308%

    No Known Activations