© 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. 65721
    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
     TÉCNICA
    -1.43
    EMOS
    -1.30
    Więcej
    -1.30
    lampe
    -1.24
     juvenil
    -1.21
     bancada
    -1.21
     Temporada
    -1.20
     MÁS
    -1.20
     TÉCN
    -1.20
     Serviço
    -1.17
    POSITIVE LOGITS
    u
    1.13
    z
    1.13
     古着
    1.13
     such
    1.12
    </h2>
    1.12
    li
    1.11
          
    1.07
    wa
    1.06
      
    1.05
    ine
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.