© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12741
    Prev
    Next
    INDEX
    Explanations

    corporate and enterprise business terms

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

    The neuron primarily detects mentions of corporate or business–related terms (especially the word “corporate”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ଃ
    0.61
     populous
    0.60
     currants
    0.60
    备注
    0.59
     congested
    0.58
     nuts
    0.58
    প্ট
    0.57
     HELP
    0.57
    dyž
    0.57
    썸
    0.57
    POSITIVE LOGITS
    Corporate
    1.02
     Corporate
    0.98
    corporate
    0.98
     Headquarters
    0.87
    logos
    0.82
    wide
    0.80
     corporate
    0.80
     headquarters
    0.79
     корпора
    0.78
     logos
    0.77
    Activations Density 0.139%

    No Known Activations