© 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. 115660
    Prev
    Next
    INDEX
    Explanations

    IF NOT EXISTS code

    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
     Lait
    -0.73
    iomanip
    -0.71
    Convention
    -0.69
     tộc
    -0.69
    Stage
    -0.69
    ieuse
    -0.68
    Ozone
    -0.68
     ozone
    -0.67
    告訴
    -0.67
    мость
    -0.66
    POSITIVE LOGITS
    控
    0.70
    WRAPPER
    0.69
    ());//
    0.68
    基本
    0.68
    ган
    0.66
     synerg
    0.66
    EAN
    0.65
    ܫ
    0.65
    Amal
    0.64
    ან
    0.63
    Activations Density 0.061%

    No Known Activations