© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86652
    Prev
    Next
    INDEX
    Explanations

    closing tags and separators

    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
    \
    -2.30
     he
    -1.86
     
    -1.80
    <blockquote>
    -1.79
    at
    -1.73
    翃
    -1.67
    されていた
    -1.67
    และ
    -1.66
    imenti
    -1.64
     cuyos
    -1.63
    POSITIVE LOGITS
    Они
    2.17
    獁
    2.02
     didik
    1.99
    𞤢
    1.99
    t
    1.97
     querían
    1.96
    jmniej
    1.88
    ープン
    1.88
    
    1.85
    </h4>
    1.83
    Activations Density 0.002%

    No Known Activations