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. 199
    Prev
    Next
    INDEX
    Explanations

    descriptive word followed by concept

    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
    пери
    -0.93
    
    -0.91
    atuur
    -0.85
    ês
    -0.83
    HasColumn
    -0.79
    teins
    -0.77
     '-')
    -0.77
    ribute
    -0.77
    fusions
    -0.76
    лку
    -0.75
    POSITIVE LOGITS
     structure
    0.92
     Strukt
    0.83
     encountered
    0.82
     bandai
    0.78
    breve
    0.78
     Kaspersky
    0.76
     Maroon
    0.75
     Andorra
    0.75
    inaire
    0.74
     communication
    0.74
    Activations Density 0.024%

    No Known Activations