© 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. 10-GEMMASCOPE-RES-131K
    7. 41597
    Prev
    Next
    INDEX
    Explanations

    political party names

    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_10/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
     the
    -2.25
    Three
    -1.84
     and
    -1.84
    詳しくは
    -1.78
    This
    -1.78
    三個
    -1.77
    的情況
    -1.77
     zapro
    -1.77
    過程中
    -1.70
     ataupun
    -1.69
    POSITIVE LOGITS
    <td>
    2.03
    ❮
    1.80
    ===============
    1.80
    =============
    1.73
    」、「
    1.72
     vols
    1.70
     adulta
    1.70
    」(
    1.66
    ₩
    1.66
    viembre
    1.65
    Activations Density 0.009%

    No Known Activations