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. 8242
    Prev
    Next
    INDEX
    Explanations

    library and code snippets

    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
     chré
    -0.91
     voedsel
    -0.90
    oversized
    -0.90
     begele
    -0.89
    Примеры
    -0.87
     can
    -0.85
     geschreven
    -0.84
    joey
    -0.84
     begleitet
    -0.82
    ROBERT
    -0.81
    POSITIVE LOGITS
     casualties
    1.01
     stakeholders
    1.00
     filter
    0.99
    figsize
    0.99
     filters
    0.97
    ﻷ
    0.96
     dropdown
    0.96
     всех
    0.94
     пальто
    0.92
     fatalities
    0.92
    Activations Density 0.003%

    No Known Activations