© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110617
    Prev
    Next
    INDEX
    Explanations

    enterprise business software

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

    the word "enterprise" in business and technology contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on occurrences of the word “enterprise,” especially in compound business/tech phrases (e.g. “enterprise software,” “enterprise security”).

    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
     ジップ
    -2.14
     juſt
    -2.03
    縢
    -2.02
     Erinnerungen
    -2.00
    despite
    -1.94
    ᷆
    -1.93
    熥
    -1.92
    ꔹ
    -1.90
    を楽しむ
    -1.89
    🦣
    -1.88
    POSITIVE LOGITS
    f
    2.34
    //
    2.30
    ve
    2.17
    da
    2.03
     of
    1.90
     exquisite
    1.88
     exquisitely
    1.87
    from
    1.87
    we
    1.86
     Both
    1.80
    Activations Density 0.010%

    No Known Activations