© 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. 22187
    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
    ポーター
    -0.94
    žné
    -0.94
     normalerweise
    -0.93
     coupled
    -0.93
     niemals
    -0.91
    إذا
    -0.90
     zwar
    -0.89
    حتى
    -0.89
     نمک
    -0.88
    pincode
    -0.87
    POSITIVE LOGITS
    カタログ
    0.98
     Macht
    0.92
     möchte
    0.91
    asta
    0.90
     Made
    0.89
     Leeds
    0.89
    其妙
    0.89
     vì
    0.89
     Determin
    0.88
     GOD
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.