© 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. 110484
    Prev
    Next
    INDEX
    Explanations

    value = or :

    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
     tentando
    -1.54
    螣
    -1.45
    讓我們
    -1.39
    ೣ
    -1.39
     necessária
    -1.36
     détermination
    -1.36
    ܆
    -1.34
     frequentemente
    -1.34
     美しい
    -1.32
     its
    -1.28
    POSITIVE LOGITS
    .
    1.68
    Some
    1.57
    These
    1.55
    Using
    1.52
    Both
    1.50
    Although
    1.50
    0
    1.48
    :
    1.48
     като
    1.48
    There
    1.45
    Activations Density 0.002%

    No Known Activations