© 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. 102599
    Prev
    Next
    INDEX
    Explanations

    slice, politics, copyright

    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
     Metodo
    -0.83
    おしゃれ
    -0.75
     преступ
    -0.75
     feind
    -0.72
    relationship
    -0.72
     caldo
    -0.72
     coiled
    -0.70
    ्र
    -0.70
     angelo
    -0.69
    Bibliografia
    -0.69
    POSITIVE LOGITS
    琢
    0.89
     slicing
    0.85
     slice
    0.84
     Slice
    0.81
     slicer
    0.79
    菖
    0.77
    Abund
    0.74
     hidratante
    0.74
     femenina
    0.73
    tako
    0.73
    Activations Density 0.012%

    No Known Activations