© 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. 59764
    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
    または
    -1.08
    ఠ
    -1.02
     Paglinawan
    -0.98
    ா
    -0.96
    Ẽ
    -0.93
    ilent
    -0.93
    μα
    -0.93
     treball
    -0.93
    vato
    -0.92
    regate
    -0.91
    POSITIVE LOGITS
     before
    0.91
    title
    0.88
    ादी
    0.88
     Tipos
    0.88
    の通り
    0.86
     simply
    0.84
    此前
    0.83
     thérape
    0.82
     refiere
    0.81
     cuaderno
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.