© 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. 22-GEMMASCOPE-RES-131K
    7. 34270
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     will
    -1.13
     of
    -1.00
    というもの
    -0.94
    tiglie
    -0.93
    onym
    -0.91
     to
    -0.91
     Musiker
    -0.88
     søndag
    -0.87
     when
    -0.86
    ükü
    -0.85
    POSITIVE LOGITS
     anatomic
    0.94
    spanning
    0.93
     outlier
    0.93
     amitié
    0.92
    льники
    0.90
    יקה
    0.90
    Hilsen
    0.90
    即便是
    0.88
     sobretudo
    0.88
    onka
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.