© 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. 13022
    Prev
    Next
    INDEX
    Explanations

    code delimiters and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    等は
    -1.02
     geheim
    -0.98
    specifically
    -0.96
     GRADUATE
    -0.95
     assorted
    -0.95
    ategorised
    -0.93
    ulism
    -0.90
     ACROSS
    -0.88
     PRESENTED
    -0.87
     všetky
    -0.86
    POSITIVE LOGITS
     lavori
    0.90
    يج
    0.89
     Grom
    0.88
     one
    0.87
     भी
    0.85
     mettere
    0.85
     вересня
    0.83
     razonable
    0.83
     durfte
    0.82
     taken
    0.79
    Activations Density 0.018%

    No Known Activations