© 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. 22-GEMMASCOPE-RES-131K
    7. 26972
    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
     its
    -1.53
     it
    -1.29
     to
    -1.02
     all
    -1.01
    它
    -0.97
     latter
    -0.96
     abgerufen
    -0.93
     because
    -0.88
    ҫ
    -0.86
    xmax
    -0.85
    POSITIVE LOGITS
     gioia
    1.27
     réparer
    1.14
    همچنین
    1.07
     biedt
    1.06
     продолжает
    1.05
    المصادر
    1.04
     Bagaimana
    1.04
     Berikut
    1.03
     opulent
    1.03
    Yar
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.