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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130
    Prev
    Next
    INDEX
    Explanations

    CWE followed by numbers

    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_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
     This
    -1.96
    </h2>
    -1.95
    </h1>
    -1.92
     The
    -1.91
     It
    -1.62
     While
    -1.54
     or
    -1.44
     That
    -1.44
    This
    -1.42
     There
    -1.42
    POSITIVE LOGITS
     that
    1.56
     desn
    1.50
     obvio
    1.48
     afront
    1.48
     incrí
    1.38
     jist
    1.36
     récemment
    1.34
    奩
    1.34
     espect
    1.34
    implies
    1.33
    Activations Density 0.005%

    No Known Activations