© 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. 78863
    Prev
    Next
    INDEX
    Explanations

    elastic net, lasso, regression

    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
     libertad
    -0.76
     villain
    -0.75
    мл
    -0.74
    ikkert
    -0.73
    телю
    -0.73
    bored
    -0.73
    訕
    -0.71
     valign
    -0.71
     Limits
    -0.71
     bons
    -0.71
    POSITIVE LOGITS
     Elastic
    1.24
    enet
    1.09
     penalty
    1.06
    Elastic
    1.05
     elastic
    1.01
     lasso
    0.94
     solvers
    0.93
     regularization
    0.91
     Lasso
    0.90
    elastic
    0.89
    Activations Density 0.032%

    No Known Activations