© 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. 12287
    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
    prilis
    -1.10
    ”？
    -1.02
     votre
    -1.00
     navegador
    -0.98
     than
    -0.98
     espirituales
    -0.97
    ”、“
    -0.94
     σας
    -0.94
    urman
    -0.94
    zweig
    -0.93
    POSITIVE LOGITS
     finalize
    0.93
     wok
    0.86
     rendement
    0.86
     restring
    0.86
     DERE
    0.84
     LOCATIONS
    0.84
    assume
    0.83
    특
    0.83
     plancha
    0.83
     dios
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.