© 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. 92221
    Prev
    Next
    INDEX
    Explanations

    generic object data source

    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
    ‿
    -0.72
    ✖
    -0.68
    iální
    -0.66
    вления
    -0.66
     määrä
    -0.64
    Inflater
    -0.64
    Lindsey
    -0.63
    okka
    -0.62
    clare
    -0.62
     Granada
    -0.62
    POSITIVE LOGITS
     assert
    0.72
     einzigartige
    0.71
     使用
    0.69
    QSize
    0.68
     недо
    0.68
     ahorro
    0.68
    posten
    0.68
    anema
    0.67
    ダード
    0.66
     CTS
    0.66
    Activations Density 0.048%

    No Known Activations