© 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. 22-GEMMASCOPE-RES-131K
    7. 73590
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    hanno
    -1.12
     Jenderal
    -1.02
     herren
    -1.01
    chemise
    -0.98
     damen
    -0.98
    并
    -0.97
     rame
    -0.94
    两个
    -0.93
    ък
    -0.93
     Rabu
    -0.91
    POSITIVE LOGITS
    的对象
    1.07
    excellents
    1.06
     azonban
    1.02
    取决
    1.02
    borderBottom
    1.01
    ⟝
    1.01
     podríamos
    0.98
    全是
    0.98
    やってる
    0.98
     tudo
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.