© 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. 11596
    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
    ↵
    -1.33
     both
    -1.27
     både
    -1.23
     matériau
    -1.16
    셜
    -1.13
     Cela
    -1.11
    weiß
    -1.11
     दिया
    -1.09
     WONDER
    -1.08
     Lk
    -1.08
    POSITIVE LOGITS
     following
    1.79
     notícia
    1.49
    especially
    1.46
    悫
    1.45
    的其他
    1.44
    .”
    1.38
    鸶
    1.34
     same
    1.33
     praça
    1.31
     nuvem
    1.31
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.