© 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. 99821
    Prev
    Next
    INDEX
    Explanations

    pleaded guilty

    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
    𓐍
    -2.91
    鈊
    -2.67
                
    -2.61
        
    -2.53
     действия
    -2.48
    羽毛
    -2.48
    𖤍
    -2.44
                    
    -2.42
     {
    -2.36
     für
    -2.34
    POSITIVE LOGITS
     parachoque
    2.48
    明日は
    2.33
     accedi
    2.31
    iſter
    2.28
    赑
    2.23
    𐑂
    2.17
    今度
    2.16
     aktivieren
    2.16
     Vgl
    2.13
    みんなで
    2.11
    Activations Density 0.003%

    No Known Activations