© 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. 15005
    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
     اصلا
    -0.98
     приходится
    -0.90
    旁边的
    -0.89
     suun
    -0.89
    ają
    -0.88
    Nemo
    -0.88
     penutup
    -0.88
    手的
    -0.87
    że
    -0.84
    そうだ
    -0.84
    POSITIVE LOGITS
     brauchst
    1.02
     Feinde
    0.99
    桃園
    0.98
    ΤΟ
    0.97
    bitmap
    0.95
    vák
    0.92
    Những
    0.91
    espère
    0.91
    eltzer
    0.91
    ={},
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.