© 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. 1911
    Prev
    Next
    INDEX
    Explanations

    companies and providers

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

    The neuron fires on prominent technical or domain-specific jargon and keyword terms (e.g. SEO, frame, wind, card, genetics, cable, interface, microchip).

    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
    ḩ
    -0.85
    员工
    -0.84
    Patients
    -0.84
    patients
    -0.84
    ciencia
    -0.81
    {}
    -0.79
    betic
    -0.78
    笅
    -0.76
    ÜN
    -0.75
    }*
    -0.75
    POSITIVE LOGITS
     companies
    4.41
     company
    3.97
     providers
    3.59
     provider
    3.56
     supplier
    3.11
     firms
    3.06
     Companies
    2.95
     suppliers
    2.94
    Companies
    2.77
    companies
    2.73
    Activations Density 0.212%

    No Known Activations