© 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. 112644
    Prev
    Next
    INDEX
    Explanations

    limited liability company

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

    The neuron detects references to legal business entity types (e.g., LLC, limited liability company, partnership).

    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
     gomma
    -1.34
    mitive
    -1.34
    + 
    -1.32
     préstamos
    -1.31
    rure
    -1.31
     schli
    -1.30
     mús
    -1.27
     zitate
    -1.24
    fche
    -1.24
    tiet
    -1.24
    POSITIVE LOGITS
    </h2>
    1.48
    </h3>
    1.25
    ).
    1.23
    ্
    1.19
    Каждый
    1.18
    <i>
    1.16
    ot
    1.16
    To
    1.16
    this
    1.15
    This
    1.14
    Activations Density 0.028%

    No Known Activations