© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127732
    Prev
    Next
    INDEX
    Explanations

    error handling Exception

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     渋谷
    -0.85
     Jupyter
    -0.83
    ᅮ
    -0.82
    gebnis
    -0.76
    dium
    -0.75
    ѓ
    -0.74
    juego
    -0.73
     runnable
    -0.72
     JN
    -0.70
    椀
    -0.69
    POSITIVE LOGITS
    فين
    0.87
     recomendaciones
    0.85
    Lung
    0.85
     mismo
    0.82
     message
    0.81
    niger
    0.81
     informative
    0.79
     lámparas
    0.79
    ameter
    0.79
     торт
    0.79
    Activations Density 0.005%

    No Known Activations