© 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. 29138
    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
     roadway
    -1.00
    犼
    -0.98
     Utiliz
    -0.96
     nost
    -0.95
    luo
    -0.94
    fei
    -0.93
     finalised
    -0.93
    iked
    -0.91
    thru
    -0.91
     proposto
    -0.91
    POSITIVE LOGITS
    شاف
    0.96
     jestli
    0.88
    竿
    0.86
     اگر
    0.86
    РОВ
    0.84
     отдыха
    0.84
    youtube
    0.84
    давно
    0.83
     went
    0.82
    ध्य
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.