© 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. 107371
    Prev
    Next
    INDEX
    Explanations

    established or launched companies

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

    The neuron detects mentions of organizations or companies (including their names, founders, and corporate context).

    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
    因为它
    -0.89
     Danish
    -0.88
     boasts
    -0.87
    opress
    -0.85
     minutter
    -0.84
    </td>
    -0.83
    ėl
    -0.81
     Trotsky
    -0.81
    海军
    -0.81
     local
    -0.81
    POSITIVE LOGITS
     his
    1.16
    employees
    1.03
     terem
    1.01
    Employees
    0.99
    vehicles
    0.93
     그의
    0.88
     camuf
    0.87
     parfums
    0.83
    responseType
    0.83
    projekt
    0.83
    Activations Density 0.092%

    No Known Activations