© 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. 22-GEMMASCOPE-RES-131K
    7. 38741
    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
     fön
    -1.12
    ouvre
    -1.11
    tegen
    -0.89
     ecles
    -0.88
    ":["
    -0.86
    dungen
    -0.86
     politika
    -0.85
     minus
    -0.84
    mited
    -0.83
    born
    -0.83
    POSITIVE LOGITS
    Nhi
    0.92
     Closes
    0.90
    México
    0.89
    不仅仅
    0.88
    Sudan
    0.86
    zusch
    0.85
     entdeckt
    0.85
    nhi
    0.85
     gebeten
    0.84
    selbe
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.