© 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. 34901
    Prev
    Next
    INDEX
    Explanations

    legal rights and procedural fairness

    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
    IORITY
    -0.77
     buono
    -0.73
     игру
    -0.71
     Candid
    -0.70
    eiras
    -0.69
    ガンダム
    -0.68
    uestas
    -0.68
     Tame
    -0.66
    責任
    -0.66
    uldron
    -0.65
    POSITIVE LOGITS
     due
    3.47
    due
    3.00
     Due
    2.94
    Due
    2.88
     DUE
    2.59
    DUE
    2.23
     devido
    2.13
     debido
    2.11
     procedural
    1.99
     process
    1.74
    Activations Density 0.026%

    No Known Activations