© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15810
    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
    kei
    -0.99
     tromper
    -0.93
    つまみ
    -0.92
     quase
    -0.91
    骉
    -0.90
    蓠
    -0.90
    ཿ
    -0.90
     gerekti
    -0.90
    éras
    -0.88
     Cette
    -0.88
    POSITIVE LOGITS
     unparalleled
    0.98
     had
    0.97
     just
    0.94
     насеља
    0.94
    mRecyclerView
    0.94
    dyti
    0.93
    ΡΟ
    0.91
     menurun
    0.91
     When
    0.91
    stringValue
    0.90
    Activations Density 0.000%

    No Known Activations