© 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. 79652
    Prev
    Next
    INDEX
    Explanations

    special characters and capitalization

    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
     such
    -0.90
    /$',
    -0.89
     Group
    -0.89
    InitStructure
    -0.88
     R
    -0.86
    关于
    -0.83
    group
    -0.82
     called
    -0.82
     along
    -0.81
    icon
    -0.81
    POSITIVE LOGITS
    gencias
    1.03
    強調
    0.98
    Това
    0.96
    Ирина
    0.92
    tså
    0.92
    Ольга
    0.92
    peka
    0.91
     quelques
    0.91
    Parfait
    0.90
    Бар
    0.87
    Activations Density 0.093%

    No Known Activations