© 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. 34-GEMMASCOPE-RES-131K
    7. 11770
    Prev
    Next
    INDEX
    Explanations

    questions and markdown

    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_34/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
     from
    -1.31
    陪
    -0.81
    rible
    -0.79
    ﹋
    -0.76
    Comentarios
    -0.76
     infatti
    -0.75
    guards
    -0.75
    oblastoma
    -0.74
     scuola
    -0.73
    stdbool
    -0.73
    POSITIVE LOGITS
    main
    0.96
     content
    0.92
     page
    0.89
    PAGE
    0.88
     bread
    0.85
    RAEL
    0.84
    тко
    0.84
    中间
    0.81
     Page
    0.81
     main
    0.81
    Activations Density 0.014%

    No Known Activations