© 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. 8239
    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
     perpé
    -1.13
     maniere
    -1.09
    нении
    -1.04
     fallecido
    -1.02
    铪
    -1.01
    怎么说
    -1.00
    
    -0.98
     nemá
    -0.97
     ktorí
    -0.96
     škoda
    -0.94
    POSITIVE LOGITS
     their
    1.38
     those
    1.28
     some
    1.24
     three
    1.13
     five
    1.09
     this
    1.09
     one
    1.09
     fifteen
    1.05
     both
    1.00
     help
    0.98
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.