© 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. 68598
    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
    блиоте
    -0.88
    efd
    -0.87
    >.
    -0.87
    但不
    -0.86
    Jul
    -0.86
     pomy
    -0.85
     Nat
    -0.85
     салона
    -0.84
    Feb
    -0.84
     manager
    -0.83
    POSITIVE LOGITS
     eſſ
    1.09
     comesti
    1.06
     Vitória
    0.99
    特有
    0.98
     riva
    0.97
     penna
    0.94
     positioned
    0.94
     sny
    0.93
     minuter
    0.92
    íficos
    0.92
    Activations Density 0.000%

    No Known Activations