© 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. 56018
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
     cenu
    -0.84
     habría
    -0.79
     Fig
    -0.78
    arnings
    -0.77
    chedule
    -0.76
     еды
    -0.75
    вес
    -0.74
    ňte
    -0.74
     Burnett
    -0.73
    🤡
    -0.73
    POSITIVE LOGITS
     Frontiers
    1.06
    Fron
    0.93
     Fron
    0.90
     anesthe
    0.87
     doveva
    0.82
    owi
    0.80
     Tallahassee
    0.80
     Zacks
    0.80
     SiO
    0.78
     refraction
    0.77
    Activations Density 0.017%

    No Known Activations