© 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. 12664
    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
    -1.05
    ieme
    -0.93
     calavera
    -0.93
     its
    -0.92
    ήσει
    -0.89
    のではない
    -0.86
    transparent
    -0.86
     espir
    -0.85
    vège
    -0.85
     tambor
    -0.85
    POSITIVE LOGITS
    matmul
    0.92
     также
    0.92
    /*++
    0.91
    &
    0.91
     mellow
    0.90
     reptile
    0.90
     можете
    0.90
    /*!
    0.90
     notamment
    0.89
    LC
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.