© 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. 12790
    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
    глежда
    -0.94
     kirj
    -0.94
     this
    -0.93
     Dě
    -0.92
     września
    -0.92
    ㉨
    -0.91
    和
    -0.90
    $,
    -0.90
    mesan
    -0.88
     dismiss
    -0.87
    POSITIVE LOGITS
    Toda
    1.10
     чрез
    1.05
    粼
    1.05
    ating
    1.03
     aforementioned
    1.01
     protože
    1.01
    嫖
    0.98
    mentioned
    0.98
    ater
    0.97
     whole
    0.97
    Activations Density 0.000%

    No Known Activations