© 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. 7683
    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
    entista
    -0.95
    trường
    -0.93
    Authority
    -0.92
    wortet
    -0.92
    枚
    -0.90
    มา
    -0.89
     aconte
    -0.88
    nání
    -0.85
    ствовать
    -0.84
    cocci
    -0.84
    POSITIVE LOGITS
     misinformation
    1.01
    4
    0.98
     ermöglich
    0.95
     berikan
    0.93
    ></
    0.91
    0
    0.89
     fakes
    0.88
     sawdust
    0.87
    In
    0.86
     weaves
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.