© 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. 5888
    Prev
    Next
    INDEX
    Explanations

    company and legal entity suffixes

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

    The neuron flags corporate legal‐entity designators (e.g. “Inc.”, “Ltd.”, “Corp.”, “LLC,” etc.) following company names.

    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
    ಂಟು
    0.56
     crónica
    0.55
     personalities
    0.54
    正常的
    0.53
    跳
    0.53
     کرام
    0.53
    Personality
    0.53
    즙
    0.53
    宦
    0.52
    সম
    0.52
    POSITIVE LOGITS
     कंपनी
    0.84
     COMPANY
    0.80
     şirket
    0.80
     Company
    0.80
    子公司
    0.79
     subsidiaries
    0.78
     公司
    0.78
    .,
    0.76
     કંપની
    0.70
     kompan
    0.68
    Activations Density 0.109%

    No Known Activations