© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 84430
    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
     using
    -1.24
     out
    -1.19
    Using
    -1.13
    EMOS
    -1.08
    erweise
    -1.01
     doing
    -1.00
     The
    -0.98
     estreia
    -0.98
    بوع
    -0.98
     put
    -0.98
    POSITIVE LOGITS
    particularly
    1.34
     ۔
    1.33
     generell
    1.30
     культура
    1.23
    Frage
    1.20
     SPECIFIC
    1.18
    ESPEC
    1.15
     MIKE
    1.15
    嗳
    1.13
    unków
    1.12
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.