© 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. 99335
    Prev
    Next
    INDEX
    Explanations

    clean following text

    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
    </strong>
    -1.63
    </h1>
    -1.42
          
    -1.34
    巂
    -1.34
    ("")]
    -1.32
    スカート
    -1.31
     
    -1.29
            
    -1.28
         
    -1.27
     be
    -1.27
    POSITIVE LOGITS
     clean
    2.02
    clean
    1.89
    
    1.70
     Cleaner
    1.62
     cleaned
    1.62
     sạch
    1.60
     Clean
    1.58
    Clean
    1.54
    There
    1.48
    Médaille
    1.45
    Activations Density 0.053%

    No Known Activations