© 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. 128859
    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
     resulting
    -1.13
     other
    -1.08
    を
    -1.02
    更何况
    -1.02
     small
    -1.01
     struggles
    -0.97
     by
    -0.96
     zusätzlichen
    -0.96
     people
    -0.95
     sicheren
    -0.94
    POSITIVE LOGITS
     ванной
    1.10
    AndSet
    1.08
     néer
    1.05
     pizarra
    1.00
     délais
    0.98
     kredi
    0.98
     aço
    0.97
    鬭
    0.97
     publicKey
    0.97
    🪂
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.