© 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. 22-GEMMASCOPE-RES-131K
    7. 26381
    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
    now
    -0.95
    的
    -0.92
     now
    -0.92
    他的
    -0.91
    0
    -0.90
     Nederlandse
    -0.89
     柜
    -0.89
    int
    -0.88
    想要
    -0.86
    要在
    -0.85
    POSITIVE LOGITS
    闈
    1.12
    抬起头
    1.09
     aplicable
    1.03
     around
    1.01
     comedor
    0.99
    ピュ
    0.98
     opér
    0.97
    🪦
    0.97
     vanguardia
    0.97
     ujar
    0.97
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.