© 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. 111129
    Prev
    Next
    INDEX
    Explanations

    numbers AND dates

    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
    Columbus
    -0.74
     unreliable
    -0.73
     Columbus
    -0.71
    thington
    -0.68
     Corvette
    -0.68
     gør
    -0.68
    logique
    -0.68
    ürtel
    -0.67
     Beckett
    -0.66
    rads
    -0.66
    POSITIVE LOGITS
    ConnectionString
    0.77
    selectAll
    0.77
     Aung
    0.76
    bilder
    0.75
     Fairfax
    0.73
     Allianz
    0.71
    ╰
    0.71
    辫
    0.70
    grpc
    0.70
     Patil
    0.69
    Activations Density 0.013%

    No Known Activations