© 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. 2153
    Prev
    Next
    INDEX
    Explanations

    companies and corporations

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

    This neuron specializes in spotting names of corporate or organizational entities, especially multiword company names and their acronyms.

    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
    ʛ
    0.74
    mehndi
    0.71
     Amish
    0.70
     homeschool
    0.68
     bootcamp
    0.67
     Clooney
    0.65
    教堂
    0.65
     Buckeyes
    0.65
     Shopify
    0.63
     컬
    0.63
    POSITIVE LOGITS
     subsidiaries
    1.45
     monopolies
    1.28
     subsidiary
    1.25
     monopoly
    1.25
     Corporation
    1.24
     corporation
    1.23
     privatisation
    1.20
     privatization
    1.18
     monopol
    1.13
     perusahaan
    1.12
    Activations Density 0.537%

    No Known Activations