© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 19807
    Prev
    Next
    INDEX
    Explanations

    U.S. Supreme Court cases

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

    The neuron detects the numerical components (volume and page numbers or years) in formal legal 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_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
    或者是
    -1.84
    '
    -1.66
    该如何
    -1.59
     like
    -1.55
    就是一个
    -1.54
     or
    -1.53
    可在
    -1.45
     can
    -1.45
     pudieron
    -1.45
    t
    -1.43
    POSITIVE LOGITS
     apó
    1.63
     NSCoder
    1.58
     ส์
    1.53
    casino
    1.52
     "];
    1.51
                             
    1.46
    следования
    1.46
    ☫
    1.45
     saia
    1.45
    ↵
    1.44
    Activations Density 0.037%

    No Known Activations