© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86133
    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
     获取
    -1.19
     riferimento
    -1.03
    immen
    -1.03
    schedulers
    -1.02
     there
    -1.02
    可以
    -0.99
     should
    -0.99
    嗚
    -0.98
     gelieb
    -0.98
     Notably
    -0.97
    POSITIVE LOGITS
    龊
    1.13
    少的
    1.05
    knows
    1.01
     elemen
    0.98
     لوازم
    0.98
     servent
    0.97
    一堆
    0.95
     slams
    0.94
     соревно
    0.94
     HOTEL
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.