© 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. 11608
    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
    </h1>
    -1.58
    𝐨
    -1.55
    里面
    -1.48
    ats
    -1.47
     YOUR
    -1.46
    is
    -1.44
     снова
    -1.41
    </h5>
    -1.41
    ？！”
    -1.37
    ﮩ
    -1.37
    POSITIVE LOGITS
    0
    1.43
     following
    1.43
    氳
    1.38
    asserole
    1.31
     freundlichen
    1.29
    叹了口气
    1.28
    瞟
    1.28
     Kälte
    1.27
    思索
    1.27
     tiefe
    1.27
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.