© 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. 35814
    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
     now
    -1.22
     even
    -1.20
     still
    -1.19
     content
    -1.09
     και
    -1.04
    üle
    -0.99
     lay
    -0.99
     Vierge
    -0.96
     accurately
    -0.96
     ткань
    -0.96
    POSITIVE LOGITS
     jambes
    1.24
     genoux
    1.20
     lucru
    1.10
    割と
    1.09
     mogli
    1.06
     '**
    1.06
    わけです
    1.03
     ongles
    1.02
     áng
    1.02
     logements
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.