© 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. 82779
    Prev
    Next
    INDEX
    Explanations

    GLA rights

    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
    メット
    -0.81
     Deeper
    -0.77
     除
    -0.75
    LoggerFactory
    -0.75
     BBM
    -0.75
     dag
    -0.71
     Tert
    -0.70
     بني
    -0.70
     cellar
    -0.69
     Autorin
    -0.69
    POSITIVE LOGITS
    SqlConnection
    0.79
    знание
    0.75
    decoration
    0.73
    ItemView
    0.72
    Поль
    0.71
    Accumulator
    0.71
     profeta
    0.71
    Diámetro
    0.71
    lineWidth
    0.70
    NSData
    0.70
    Activations Density 0.017%

    No Known Activations