© 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. 15229
    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
     圣诞
    -1.11
     meni
    -1.02
     插图
    -1.02
    刧
    -1.00
    ULTURAL
    -0.96
     fernando
    -0.96
     搞笑
    -0.94
     arv
    -0.93
     艺术
    -0.93
     dira
    -0.93
    POSITIVE LOGITS
     Bestimm
    1.07
     Häufig
    1.06
     acces
    1.05
    限制
    1.02
    居住
    0.99
     satisfe
    0.99
    sibirsk
    0.96
     hurdles
    0.95
     again
    0.94
    |;
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.