© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108389
    Prev
    Next
    INDEX
    Explanations

    proportion

    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
     huden
    -0.93
     båda
    -0.89
     atributos
    -0.86
     ganska
    -0.85
     Rptr
    -0.83
     datetime
    -0.82
    ouss
    -0.81
     análisis
    -0.80
    estimate
    -0.79
    Dracula
    -0.79
    POSITIVE LOGITS
     пропор
    0.93
     dennoch
    0.89
     proportional
    0.87
     proportion
    0.81
    今でも
    0.80
     proportions
    0.79
     proportionality
    0.78
     escor
    0.78
     proportionally
    0.77
    比例
    0.76
    Activations Density 0.010%

    No Known Activations