Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8286
    Prev
    Next
    INDEX
    Explanations

    workstation professional

    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
     Obf
    -0.78
    CSharp
    -0.77
     Aún
    -0.73
    cznego
    -0.72
    époque
    -0.72
    品です
    -0.71
     pertenecen
    -0.70
     belonged
    -0.70
    setTypeface
    -0.69
     Había
    -0.68
    POSITIVE LOGITS
     workstation
    1.56
     professional
    1.45
    professional
    1.30
     Professional
    1.30
     профессиона
    1.25
    Professional
    1.23
     profesional
    1.23
     workstations
    1.20
     Workstation
    1.14
     profesjonal
    1.13
    Activations Density 0.023%

    No Known Activations