© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116902
    Prev
    Next
    INDEX
    Explanations

    center or middle

    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
    ioma
    -0.82
     UIFont
    -0.79
    Areas
    -0.78
     cuáles
    -0.77
    dracht
    -0.76
    €¦
    -0.75
     móveis
    -0.73
    ürme
    -0.73
     capilar
    -0.73
    Mover
    -0.73
    POSITIVE LOGITS
     center
    4.97
     centre
    4.41
    center
    3.66
    centre
    3.09
     центре
    2.88
     центр
    2.81
    中心
    2.80
    CENTER
    2.75
     centers
    2.69
     middle
    2.67
    Activations Density 0.068%

    No Known Activations