© 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. 65032
    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
     luckily
    -1.00
     femei
    -0.98
     resented
    -0.98
     neoliber
    -0.94
    ついた
    -0.93
     succinctly
    -0.93
     δεν
    -0.93
     Magistrate
    -0.92
     fatally
    -0.92
     satisfactorily
    -0.91
    POSITIVE LOGITS
    mdash
    1.07
     one
    1.02
    strator
    0.99
     treff
    0.96
    likation
    0.95
    ⌊
    0.92
    carus
    0.92
    entown
    0.91
    тена
    0.91
     subjek
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.