© 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. 10-GEMMASCOPE-RES-131K
    7. 22307
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    することができます
    -1.18
    owanych
    -1.08
     můžete
    -1.07
    ﹔
    -1.05
     však
    -1.05
    ggish
    -1.02
    צב
    -1.02
     chcete
    -1.02
    τους
    -1.01
    engagent
    -1.01
    POSITIVE LOGITS
    ,
    0.96
    ?
    0.95
    臭
    0.88
     läs
    0.88
     extension
    0.84
      
    0.82
    ↵↵↵
    0.81
     gelb
    0.80
    extension
    0.80
     }^{
    0.80
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.