© 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. 81334
    Prev
    Next
    INDEX
    Explanations

    reaching or exceeding a limit

    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
    DirPath
    -0.88
     dépass
    -0.88
    Sản
    -0.83
    lowest
    -0.82
    aths
    -0.81
    celebr
    -0.78
     вікі
    -0.77
    retour
    -0.77
    tabela
    -0.76
     fortifications
    -0.76
    POSITIVE LOGITS
     the
    1.41
     limit
    1.29
     дозво
    0.81
    ẖ
    0.78
     jurisdictional
    0.76
    beb
    0.72
    tdb
    0.71
     There
    0.71
    Inline
    0.70
    InputStream
    0.70
    Activations Density 0.063%

    No Known Activations