© 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. 10-GEMMASCOPE-RES-131K
    7. 19736
    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
     also
    -0.98
    ſſi
    -0.97
     také
    -0.97
     !!!!!
    -0.96
     bep
    -0.96
    奁
    -0.96
     CLOSE
    -0.95
     !!!!
    -0.94
     teo
    -0.94
     oock
    -0.94
    POSITIVE LOGITS
    НИМА
    1.09
    劵
    1.06
     for
    1.06
     without
    1.01
     cautious
    0.99
     Using
    0.96
     mingle
    0.95
     relating
    0.95
     until
    0.93
    好不好
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.