© 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. 128885
    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
     their
    -1.29
    」　
    -1.17
     its
    -1.14
     constate
    -1.13
    ائدة
    -1.13
    юль
    -1.12
     anivers
    -1.11
    〜！
    -1.11
    ขอบคุณ
    -1.09
     materiaal
    -1.09
    POSITIVE LOGITS
     ‎
    1.12
     таких
    1.11
     obviamente
    1.08
     vieler
    1.07
     некоторых
    1.07
    不是很
    1.05
    z
    1.05
     alguns
    1.05
    ne
    1.02
     autén
    1.02
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.