© 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. 34-GEMMASCOPE-RES-131K
    7. 92632
    Prev
    Next
    INDEX
    Explanations

    its affiliates or subsidiaries

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

    The neuron fires on the legal‐boilerplate phrasing that enumerates a company’s affiliates or subdivisions (e.g. “and/or its various divisions and subsidiaries”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     тема
    -0.86
    гляд
    -0.85
     acknowledgement
    -0.80
     capability
    -0.77
     attitude
    -0.75
     advance
    -0.73
     Oil
    -0.72
    abril
    -0.72
    且
    -0.72
    ESO
    -0.71
    POSITIVE LOGITS
     agents
    2.36
     employees
    2.11
     affiliates
    1.85
     agent
    1.80
    agents
    1.73
    Agents
    1.52
     agentes
    1.51
     officers
    1.42
     representatives
    1.41
     assigns
    1.41
    Activations Density 0.038%

    No Known Activations