© 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. 9620
    Prev
    Next
    INDEX
    Explanations

    categories of people and their lives

    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
     these
    -1.27
     this
    -1.23
     each
    -1.15
     about
    -1.14
     using
    -1.13
     whose
    -1.08
     lados
    -1.00
     both
    -0.98
     which
    -0.95
     its
    -0.95
    POSITIVE LOGITS
     is
    1.09
     приходится
    0.99
    Fortunately
    0.99
     caminhada
    0.94
    It
    0.93
     fluff
    0.92
    lances
    0.91
     vitale
    0.91
     مرة
    0.90
    sels
    0.89
    Activations Density 0.001%

    No Known Activations