© 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. 13298
    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
     gorro
    -1.15
    
    -1.07
     criaturas
    -0.96
     päivä
    -0.96
    llavero
    -0.96
    IFYING
    -0.95
    ࿇
    -0.94
     polecam
    -0.94
     femenino
    -0.93
     Frases
    -0.93
    POSITIVE LOGITS
     by
    1.28
     to
    1.08
     Odo
    1.05
     августа
    1.04
     TELL
    1.03
     and
    1.03
    `,
    0.98
     COMPLE
    0.96
     Tempor
    0.96
     января
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.