© 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. 99963
    Prev
    Next
    INDEX
    Explanations

    mistake

    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
    錞
    -2.09
     curiously
    -2.02
     calefacción
    -1.99
    栻
    -1.98
     Houſe
    -1.94
    𞤢
    -1.89
    
    -1.88
    ："
    -1.87
    の紹介
    -1.86
     soldadura
    -1.83
    POSITIVE LOGITS
    ではでは
    2.06
    {
    1.99
    𝟭
    1.93
     if
    1.91
     BOTH
    1.88
    er
    1.86
    if
    1.81
     mistake
    1.80
     Nachdem
    1.79
    c
    1.78
    Activations Density 0.004%

    No Known Activations