© 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. 10-GEMMASCOPE-RES-131K
    7. 84291
    Prev
    Next
    INDEX
    Explanations

    court filings and legal opinions

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

    This neuron detects uppercase document headings or labels (e.g. docket headings, “ORDER,” “FILED,” etc.) that mark structural sections.

    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
    ڧ
    -1.70
     unrelenting
    -1.69
     große
    -1.66
    ↵
    -1.63
    Making
    -1.55
    Make
    -1.50
     unparalleled
    -1.48
    Having
    -1.48
     unwavering
    -1.48
    Creating
    -1.45
    POSITIVE LOGITS
    锨
    1.77
    に関しては
    1.61
     această
    1.60
     durante
    1.58
     Indeed
    1.55
     alcuni
    1.52
     alcune
    1.49
     Finally
    1.47
     in
    1.45
     lmao
    1.44
    Activations Density 0.015%

    No Known Activations