© 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. 10-GEMMASCOPE-RES-131K
    7. 130416
    Prev
    Next
    INDEX
    Explanations

    UIC, JPanel, or FileNotFound Exception

    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_10/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
    '
    -3.83
    $
    -3.23
    It
    -3.14
    -
    -2.97
    有
    -2.95
    不能
    -2.92
    ’
    -2.89
    The
    -2.84
    _
    -2.77
    2
    -2.75
    POSITIVE LOGITS
    
    2.92
    ípio
    2.92
    致します
    2.89
    珹
    2.86
     considerados
    2.84
    潾
    2.83
     daleko
    2.75
    我这
    2.72
    linawan
    2.72
    ਃ
    2.69
    Activations Density 0.002%

    No Known Activations