© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74085
    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
     découvrir
    -1.24
    helen
    -1.01
     рода
    -1.01
    aui
    -1.00
    TOO
    -0.99
    already
    -0.94
     banheiro
    -0.93
    cruiser
    -0.93
    юза
    -0.92
     tă
    -0.91
    POSITIVE LOGITS
     during
    1.20
    ・「
    1.16
     when
    0.98
    rafas
    0.93
     any
    0.91
    Having
    0.91
     know
    0.90
     throughout
    0.90
    When
    0.89
    During
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.