© 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. 86679
    Prev
    Next
    INDEX
    Explanations

    echo and its derivatives

    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
     вместе
    -2.22
     They
    -2.22
    .”
    -2.19
     Veränder
    -1.95
    </h4>
    -1.95
     it
    -1.94
     möglichen
    -1.93
     أو
    -1.91
    斂
    -1.88
     они
    -1.87
    POSITIVE LOGITS
    }
    2.23
    {
    2.08
    赑
    1.98
     Echo
    1.95
     italien
    1.91
    !«
    1.90
    után
    1.86
    鍇
    1.86
     Highlights
    1.81
    嗞
    1.81
    Activations Density 0.016%

    No Known Activations