© 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. 21695
    Prev
    Next
    INDEX
    Explanations

    if your specific item

    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
    
    -2.09
     investimento
    -1.63
    
    -1.63
     lauded
    -1.60
     unending
    -1.60
    
    -1.58
    鹪
    -1.55
    pecabe
    -1.55
    greetings
    -1.55
     tématu
    -1.52
    POSITIVE LOGITS
    :
    2.09
     JUST
    1.91
    Other
    1.90
    其他
    1.77
    If
    1.66
    すでに
    1.62
     altri
    1.60
    </strong>
    1.57
     Dí
    1.50
     anderen
    1.48
    Activations Density 0.021%

    No Known Activations