© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14016
    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
    mę
    -0.96
    valently
    -0.94
    müş
    -0.94
    δου
    -0.90
    でない
    -0.90
    一行
    -0.89
     报告
    -0.89
     this
    -0.89
    zional
    -0.88
    읍
    -0.88
    POSITIVE LOGITS
     typique
    1.08
    佩服
    1.02
     placé
    0.99
    咲
    0.98
     végétal
    0.96
    醒来
    0.95
    了个
    0.94
    ational
    0.93
     другое
    0.91
     llantas
    0.91
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.