© 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. 2995
    Prev
    Next
    INDEX
    Explanations

    law and related phrases

    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
     наи
    -0.87
     laminated
    -0.81
    вания
    -0.79
    astron
    -0.79
     curves
    -0.77
     managed
    -0.76
    activer
    -0.76
     simpto
    -0.73
    Cells
    -0.72
     hog
    -0.71
    POSITIVE LOGITS
    Ƨ
    0.80
    ଳ
    0.76
     "}";
    0.75
     Proceeds
    0.74
    elems
    0.73
     nothin
    0.73
    Gst
    0.73
     custodial
    0.72
     Hauptmann
    0.72
    LAW
    0.72
    Activations Density 0.051%

    No Known Activations