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. 8118
    Prev
    Next
    INDEX
    Explanations

    javascript code

    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
    zipped
    -0.92
    stateMutability
    -0.82
    uito
    -0.79
     userService
    -0.79
    qDebug
    -0.79
    nians
    -0.77
    uação
    -0.77
     Whatsapp
    -0.76
     Duits
    -0.75
    hast
    -0.75
    POSITIVE LOGITS
     document
    1.02
    document
    0.91
     with
    0.90
    Prototype
    0.83
     window
    0.82
     try
    0.81
     even
    0.79
     Sänger
    0.79
    YA
    0.79
     YA
    0.76
    Activations Density 0.058%

    No Known Activations