© 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. 45245
    Prev
    Next
    INDEX
    Explanations

    programming language elements

    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
     références
    -0.86
    属于
    -0.78
    entown
    -0.77
    公演
    -0.75
    ıyorum
    -0.75
     ē
    -0.73
    baikan
    -0.72
    bags
    -0.72
     komfort
    -0.72
     seguenti
    -0.71
    POSITIVE LOGITS
    测评
    0.81
    utuhkan
    0.78
    썬
    0.77
    ­
    0.77
    ager
    0.77
     comes
    0.76
     .
    0.75
    агностика
    0.75
     ..
    0.75
    initialized
    0.75
    Activations Density 0.009%

    No Known Activations