© 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. 12780
    Prev
    Next
    INDEX
    Explanations

    Python function definitions

    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
     or
    -2.28
     my
    -1.92
    te
    -1.84
    '
    -1.73
    $
    -1.66
    my
    -1.65
    k
    -1.61
    files
    -1.59
    thodox
    -1.58
    for
    -1.55
    POSITIVE LOGITS
     who
    1.87
    geox
    1.74
    schermata
    1.73
     CANNOT
    1.62
     hordes
    1.61
    誰
    1.61
     desmon
    1.60
     Não
    1.60
    暑い
    1.59
     enviada
    1.58
    Activations Density 0.013%

    No Known Activations