© 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. 116659
    Prev
    Next
    INDEX
    Explanations

    percent or percentage

    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
     آن
    -0.89
    号線
    -0.86
     $\$
    -0.82
     farewell
    -0.81
     DialogResult
    -0.79
     recompensa
    -0.79
    shadowOffset
    -0.79
     costuras
    -0.78
     BitmapFactory
    -0.77
    унд
    -0.77
    POSITIVE LOGITS
     percentage
    5.78
     percentages
    4.75
     percent
    4.66
    percentage
    4.44
    Percentage
    4.38
     Percentage
    4.28
    Percent
    3.88
    percent
    3.84
     Percent
    3.80
     porcentaje
    3.53
    Activations Density 0.091%

    No Known Activations