© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45438
    Prev
    Next
    INDEX
    Explanations

    company name

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    пси
    -0.82
    ☦
    -0.81
    ilk
    -0.81
    ervative
    -0.80
    friends
    -0.79
    getUserName
    -0.79
    ANGLE
    -0.79
     你
    -0.79
    ктора
    -0.79
     courseId
    -0.77
    POSITIVE LOGITS
     company
    3.98
     companies
    3.50
    company
    2.66
     Company
    2.64
    Company
    2.44
    CompanyName
    2.34
     corporation
    2.28
     Companies
    2.27
     organization
    2.25
     corporations
    2.22
    Activations Density 0.052%

    No Known Activations