© 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. 13028
    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
     好看
    -1.60
    扱う
    -1.52
    楽しく
    -1.46
     tasche
    -1.45
     resultat
    -1.41
    So
    -1.41
    est
    -1.41
     дове
    -1.40
    b
    -1.34
    PUESTA
    -1.32
    POSITIVE LOGITS
    leroi
    1.72
     yaklaşık
    1.60
    </sup>
    1.60
     którzy
    1.51
     cliché
    1.42
    </h4>
    1.41
     madura
    1.38
    рос
    1.38
    cleos
    1.38
    ARANCE
    1.36
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.