© 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. 9837
    Prev
    Next
    INDEX
    Explanations

    headings and labels

    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
     both
    -1.94
     with
    -1.94
     it
    -1.76
     should
    -1.75
     have
    -1.72
     from
    -1.66
     may
    -1.63
     might
    -1.62
     mainly
    -1.61
     puts
    -1.61
    POSITIVE LOGITS
     marvelous
    1.59
     fazendo
    1.55
     hablando
    1.47
     recub
    1.42
     splendid
    1.41
     fabulous
    1.38
     wondrous
    1.38
     notificaciones
    1.38
     capables
    1.38
     manteniendo
    1.37
    Activations Density 0.000%

    No Known Activations