© 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. 110696
    Prev
    Next
    INDEX
    Explanations

    ratio calculations involving factors

    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
     Springfield
    -0.80
     kalori
    -0.80
    ждународ
    -0.79
     Když
    -0.72
     Khalifa
    -0.71
    loroethene
    -0.71
     Fees
    -0.70
     Carpenter
    -0.69
     Carolina
    -0.69
     vilja
    -0.69
    POSITIVE LOGITS
     vieles
    0.98
     fator
    0.93
     f
    0.92
     factor
    0.90
     ξ
    0.90
     ratio
    0.88
     gasto
    0.88
    frac
    0.86
    eta
    0.85
     fá
    0.85
    Activations Density 0.018%

    No Known Activations