© 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. 34-GEMMASCOPE-RES-131K
    7. 63730
    Prev
    Next
    INDEX
    Explanations

    regularization and penalty terms

    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_34/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
     cashew
    -0.78
    volmente
    -0.77
     Traumatic
    -0.76
     Nostalgia
    -0.76
    柑
    -0.75
    Coordenadas
    -0.75
     Conférence
    -0.73
    ppie
    -0.73
     mercury
    -0.72
     Precautions
    -0.72
    POSITIVE LOGITS
     regularization
    2.11
     Regular
    1.91
    regular
    1.88
     regular
    1.74
     penalty
    1.73
    Regular
    1.68
     penalties
    1.66
     penal
    1.55
    penalty
    1.42
    REGULAR
    1.33
    Activations Density 0.016%

    No Known Activations