© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59648
    Prev
    Next
    INDEX
    Explanations

    taxable subjects and regulations

    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
    alkin
    -0.80
    んびり
    -0.75
    ྫ
    -0.73
     diting
    -0.73
     protective
    -0.71
     sovi
    -0.70
    Invariant
    -0.70
    ֣
    -0.70
     protecting
    -0.69
    Formik
    -0.69
    POSITIVE LOGITS
     subject
    3.75
    subject
    3.16
    Subject
    2.81
     Subject
    2.72
     subjected
    2.50
    SUBJECT
    2.34
     taxable
    2.17
     SUBJECT
    2.17
     subjects
    2.13
     subjecting
    2.08
    Activations Density 0.049%

    No Known Activations