© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113173
    Prev
    Next
    INDEX
    Explanations

    xml tags and attributes

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "key" in programming contexts, particularly in data structures, code definitions, and markup languages.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ,”
    -2.50
    ↵
    -2.42
    </h3>
    -2.31
    .
    -2.19
    …”
    -2.13
    The
    -2.08
    </i>
    -2.05
    <i>
    -1.99
    {
    -1.95
    ”,
    -1.94
    POSITIVE LOGITS
     ettiği
    1.88
    犼
    1.82
    螽
    1.82
    щают
    1.80
    寕
    1.80
    柝
    1.73
     takım
    1.70
     hän
    1.70
    
    1.70
    ILERS
    1.67
    Activations Density 0.043%

    No Known Activations