© 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. 102588
    Prev
    Next
    INDEX
    Explanations

    caught in

    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
    {
    -2.33
    \
    -1.57
    每
    -1.54
    
    -1.49
     mètres
    -1.49
     charmant
    -1.44
    ]
    -1.41
     kony
    -1.41
    ”
    -1.36
     possa
    -1.35
    POSITIVE LOGITS
     ситуация
    1.67
     sadece
    1.48
     Again
    1.47
     catches
    1.45
     caught
    1.44
     HttpNotFound
    1.39
     negociar
    1.38
     vuelve
    1.35
     вона
    1.34
     размеры
    1.34
    Activations Density 0.014%

    No Known Activations