© 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. 102405
    Prev
    Next
    INDEX
    Explanations

    legal or license boilerplate

    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
    oyo
    -0.81
    робі
    -0.79
     hati
    -0.73
    olli
    -0.71
     distin
    -0.70
     sẻ
    -0.69
    stdlib
    -0.68
    闵
    -0.68
     リボン
    -0.68
    ベージュ
    -0.67
    POSITIVE LOGITS
     كام
    0.78
     Trekking
    0.75
     Anemia
    0.75
    ortium
    0.74
    reiras
    0.73
     Endocrine
    0.71
    效率
    0.70
    yacht
    0.70
    zysz
    0.69
     ((((
    0.69
    Activations Density 0.059%

    No Known Activations