© 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. 25141
    Prev
    Next
    INDEX
    Explanations

    deviations from normal/usual

    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
    vature
    -0.84
     mohli
    -0.82
    ılır
    -0.81
    ogni
    -0.78
     Axe
    -0.78
     anuales
    -0.78
     lưng
    -0.76
    可能な
    -0.76
     fears
    -0.75
    couvrir
    -0.75
    POSITIVE LOGITS
     normal
    2.25
    normal
    1.85
     обы
    1.79
     ordinary
    1.76
     conventional
    1.66
     normale
    1.66
     usual
    1.66
    Normal
    1.58
    NORMAL
    1.57
     traditional
    1.53
    Activations Density 0.090%

    No Known Activations