© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79154
    Prev
    Next
    INDEX
    Explanations

    statistical analysis methods

    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
     Mif
    -0.89
    aktus
    -0.88
     Datasets
    -0.84
     Genocide
    -0.82
     misst
    -0.81
     Croydon
    -0.79
    Cream
    -0.77
     accelerators
    -0.75
    CHAIR
    -0.75
     EFE
    -0.74
    POSITIVE LOGITS
     Principal
    3.17
     principal
    2.94
     PCA
    2.89
    Principal
    2.88
    principal
    2.59
    PCA
    2.45
     cluster
    2.11
     PRINCIPAL
    2.09
    pca
    2.09
     principale
    1.73
    Activations Density 0.210%

    No Known Activations