© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 79855
    Prev
    Next
    INDEX
    Explanations

    questions, titles, or descriptions

    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
     with
    -2.34
     only
    -2.05
     first
    -2.03
     by
    -2.02
     for
    -2.00
     some
    -1.88
     five
    -1.86
     before
    -1.85
     every
    -1.79
     undeniably
    -1.78
    POSITIVE LOGITS
     insanely
    1.79
     horrid
    1.76
     REALLY
    1.74
    mainly
    1.74
     terrific
    1.71
     unbelievably
    1.70
     alluring
    1.70
    particularly
    1.70
     Eſ
    1.68
     AMAZING
    1.67
    Activations Density 0.003%

    No Known Activations