© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104290
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     unſ
    -0.96
    unakan
    -0.92
     leſs
    -0.87
     莫
    -0.84
     BigInteger
    -0.84
    なた
    -0.84
     yp
    -0.83
    ≔
    -0.83
     ymax
    -0.83
     ſol
    -0.81
    POSITIVE LOGITS
     low
    1.04
    lowest
    0.91
     lower
    0.91
     lowest
    0.91
     پایین
    0.90
     niž
    0.89
    Low
    0.89
    тельностью
    0.84
     less
    0.83
    Lowest
    0.83
    Activations Density 0.006%

    No Known Activations