© 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. 34-GEMMASCOPE-RES-131K
    7. 110773
    Prev
    Next
    INDEX
    Explanations

    constitutional amendments

    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
     cyclisme
    -0.88
    ⇐
    -0.77
    IModel
    -0.75
    赉
    -0.73
     londres
    -0.72
    дию
    -0.70
    匁
    -0.70
     Salto
    -0.67
    anho
    -0.67
    thys
    -0.67
    POSITIVE LOGITS
     First
    4.31
    First
    3.44
     constitutional
    3.03
     Constitutional
    2.64
     Constitution
    2.38
     constitution
    2.27
     Fourth
    2.06
     Первый
    2.06
     Пер
    2.02
     CONSTITUTION
    2.00
    Activations Density 0.078%

    No Known Activations