© 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. 38364
    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
     daban
    -1.17
     explique
    -1.09
     its
    -1.03
    телна
    -1.02
     Both
    -1.02
    ‗
    -0.99
    bilirsiniz
    -0.98
     piedras
    -0.97
    ரா
    -0.96
     there
    -0.95
    POSITIVE LOGITS
    zelfde
    1.06
    をご紹介
    1.02
     justru
    1.02
    ：……
    1.00
    同上
    0.94
    Namibia
    0.94
     notare
    0.93
     jungkook
    0.90
     GIPHY
    0.90
    símbolo
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.